Data MCP server

Pinecone MCP

Version history of discovered tools, schemas, and declared agent authority.

View watchlist

DistributionDistribution: npm
Package@pinecone-database/mcp
Latest analyzed version0.4.0
Current tool count12
Latest analysisNov 15, 2026
Package source

OBSERVED INTERFACE

Capability surface

Modelara’s observed declarations are shown separately from its derived effect classifications.

3 releases analyzed0.2.1 → 0.4.0Latest: 0.4.0
  • read8
  • write2
  • destructive2
  • unknown0

Unknown means Valyd could not determine the capability's effect confidently from the declared interface and static evidence. It is not treated as safe.

Package
@pinecone-database/mcp@0.4.0
Registry
npm
Published
Oct 29, 2026
Integrity
sha512-JewEAQw+C3vys9hWT4vMePzeP5AA8QZeHMmS4JPtYIuHZtdQRmx0o4DZZCcdXluT8dNEXM3oh1tB473vJgUA8A==
Analyzer
modelara v0.1.8 · policy not recorded
Repository
https://github.com/pinecone-io/pinecone-mcp

12 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
cascading-searchpinecone:tool:cascading-search
Observed interface and hashes

Search across multiple indexes for records that are similar to the query text, then deduplicate and rerank the combined results. Reranking is required for this tool. Only works with integrated-inference indexes. To search a single index, use search-records instead.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "indexes": {
      "description": "The indexes to search across. Records in each index should share a common schema.",
      "items": {
        "properties": {
          "name": {
            "description": "An index to search.",
            "type": "string"
          },
          "namespace": {
            "description": "A namespace to search.",
            "type": "string"
          }
        },
        "required": [
          "name",
          "namespace"
        ],
        "type": "object"
      },
      "type": "array"
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "query": {
      "description": "A query to search for records.",
      "properties": {
        "filter": {
          "additionalProperties": {},
          "description": "A filter can be used to narrow down results. Use the syntax of\n        MongoDB's query and projection operators: $eq, $ne, $gt, $gte, $lt,\n        $lte, $in, $nin, $exists, $and, $or. Make sure the records in the index\n        contain the fields that you are filtering on. To discover which fields\n        exist, run a search without a filter and inspect the \"fields\" of the\n        returned hits. Filtering on a field that records do not contain\n        returns no results.",
          "properties": {},
          "type": "object"
        },
        "inputs": {
          "properties": {
            "text": {
              "description": "The text to search for.",
              "type": "string"
            }
          },
          "required": [
            "text"
          ],
          "type": "object"
        },
        "topK": {
          "description": "The number of results to return. 10 is a reasonable default; use a\n      larger value (e.g. 50) when reranking, so the reranker has more\n      candidates to choose from. Very large values increase latency and\n      response size.",
          "type": "number"
        }
      },
      "required": [
        "topK",
        "inputs"
      ],
      "type": "object"
    },
    "rerank": {
      "description": "Specifies how the results should be reranked. Use a \"query\" with a \"topK\"\n  that returns more results than you need; then use \"rerank\" to select the\n  most relevant \"topN\" results.",
      "properties": {
        "model": {
          "description": "Choose a reranking model:\n- \"cohere-rerank-3.5\" is Cohere's leading reranking model, balancing performance\nand latency for a wide range of enterprise search applications.\n- \"bge-reranker-v2-m3\" is a high-performance, multilingual reranking model that\nworks well on messy data and short queries expected to return medium-length\npassages of text (1-2 paragraphs).\n- \"pinecone-rerank-v0\" is a state of the art reranking model that out-performs\ncompetitors on widely accepted benchmarks. It can handle chunks up to 512 tokens\n(1-2 paragraphs).",
          "enum": [
            "cohere-rerank-3.5",
            "bge-reranker-v2-m3",
            "pinecone-rerank-v0"
          ],
          "type": "string"
        },
        "query": {
          "description": "An optional query to rerank documents against. If not specified, the\n      same query will be used for both the initial search and the reranking.",
          "type": "string"
        },
        "rankFields": {
          "description": "The fields to rerank on. This should include the field name specified\n    in the index's \"fieldMap\". The \"bge-reranker-v2-m3\" and\n    \"pinecone-rerank-v0\" models support only a single rerank field.\n    \"cohere-rerank-3.5\" supports multiple rerank fields.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "topN": {
          "description": "The number of results to return after reranking. Must be less than or\n      equal to the value of \"query.topK\".",
          "type": "number"
        }
      },
      "required": [
        "model",
        "rankFields"
      ],
      "type": "object"
    }
  },
  "required": [
    "indexes",
    "query",
    "rerank"
  ],
  "type": "object"
}
sha256:c9cfa1b4ab7bfe6f7c0c0ec754daa5a09590626331f1ecb6123845b333fb37a4

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:952329bf39e5845ee9277e2488767298583426579928d4eefb981b347028bb14

Interface hash: sha256:33a64ebec3c5cc84b0e8d062f35e93c2c8a0b627d1f86c171622e95027840372

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/cascading-search",
  "title": "Cascading Search",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "cascading-search"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:33f16b0638250f51ce5983b2965369aaab803bbaf5771097baf45550a307bf5c"
}
toolread0.3.00.3.0
create-document-indexpinecone:tool:create-document-index
Observed interface and hashes

Create a Pinecone document index: an index defined by a schema of searchable "string" fields. Each field can declare "fullTextSearch" (indexed for keyword search with BM25), "embed" (Pinecone embeds the text with a hosted dense model for semantic search), "sparseEmbed" (a hosted sparse model), or a combination. A good default is one field with both, for example {"chunk_text": {"fullTextSearch": {"language": "en"}, "embed": {}}}, which supports search by meaning and by exact terms on the same text. Fields you only need to filter on are not declared here; send them as document metadata. Use upsert-documents and search-document-index with the new index. This call blocks until the index is ready. If an index with the same name already exists, it is returned unchanged instead of erroring.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "cloud": {
      "default": "aws",
      "description": "The cloud provider for the index. Defaults to aws.",
      "enum": [
        "aws",
        "gcp",
        "azure"
      ],
      "type": "string"
    },
    "fields": {
      "additionalProperties": {
        "description": "A searchable string field.",
        "properties": {
          "embed": {
            "description": "Have Pinecone embed the field's text with a hosted dense model. Pass {} for\n    the default model. An index can have at most one field with \"embed\".",
            "properties": {
              "dimension": {
                "description": "The vector dimension. Defaults to the model's default (1024).",
                "maximum": 9007199254740991,
                "minimum": -9007199254740991,
                "type": "integer"
              },
              "model": {
                "description": "A hosted dense embedding model. Defaults to \"llama-text-embed-v2\".",
                "type": "string"
              }
            },
            "type": "object"
          },
          "fullTextSearch": {
            "description": "Index the field for full-text (BM25) search. Pass {} for the defaults.",
            "properties": {
              "language": {
                "description": "The language of the text, as an ISO 639-1 code such as \"en\". Defaults to \"en\".",
                "type": "string"
              },
              "stemming": {
                "description": "Whether to stem terms. Defaults to false.",
                "type": "boolean"
              },
              "stopWords": {
                "description": "Whether to remove stop words. Requires stemming. Defaults to false.",
                "type": "boolean"
              }
            },
            "type": "object"
          },
          "sparseEmbed": {
            "description": "Have Pinecone embed the field's text with a hosted sparse model. Pass {} for\n    the default model. An index can have at most one field with \"sparseEmbed\".",
            "properties": {
              "model": {
                "description": "A hosted sparse embedding model. Defaults to \"pinecone-sparse-english-v0\".",
                "type": "string"
              }
            },
            "type": "object"
          }
        },
        "type": "object"
      },
      "description": "The searchable string fields of the index, keyed by field name.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "A unique name to identify the new index.",
      "type": "string"
    },
    "region": {
      "default": "us-east-1",
      "description": "The region for the index. Common regions: aws (us-east-1, us-west-2, eu-west-1), gcp (us-central1, europe-west1), azure (eastus, westeurope). Defaults to us-east-1.",
      "type": "string"
    }
  },
  "required": [
    "name",
    "fields"
  ],
  "type": "object"
}
sha256:90e1f666690b08a3c6ffa847553d88873a70cbe7541954e0e1486907291d8fb8

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:aaa9c72dab0c794ef365070233bb7e70ba49d8a1c687fc516fcdea21b83cb889

Interface hash: sha256:99531f9e12ffe725c74acc013a7e305cf4a5beb5068eeed08b89bf85774397fb

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/create-document-index",
  "title": "Create Document Index",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "create-document-index"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:a79f5baaed33952b1aa67bd9493d8ca79b6bc4b49871377d52eb21a8659fe0d3"
}
toolwrite0.4.00.4.0
create-index-for-modelpinecone:tool:create-index-for-model
Observed interface and hashes

Create a Pinecone index with integrated inference, which automatically embeds the text field named in "fieldMap". Supports AWS, GCP, and Azure cloud providers. This call blocks until the index is ready to accept upserts and queries, so no readiness polling is needed afterwards. If an index with the same name already exists, it is returned unchanged instead of erroring. For a new index, prefer create-document-index, which supports full-text search and integrated embedding on the same field.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "cloud": {
      "default": "aws",
      "description": "The cloud provider for the index. Defaults to aws.",
      "enum": [
        "aws",
        "gcp",
        "azure"
      ],
      "type": "string"
    },
    "embed": {
      "description": "Configure an embedding model that converts text into a vector.",
      "properties": {
        "fieldMap": {
          "description": "Identify which field from your data records will be embedded.",
          "properties": {
            "text": {
              "description": "The name of the field in the data records that contains the text\n            content to embed. Records in the index must contain this field.",
              "type": "string"
            }
          },
          "required": [
            "text"
          ],
          "type": "object"
        },
        "model": {
          "description": "Choose an embedding model:\n          - \"multilingual-e5-large\" is an efficient dense embedding model\n          trained on a mixture of multilingual datasets. It works well on messy\n          data and short queries expected to return medium-length passages of\n          text (1-2 paragraphs).\n          - \"llama-text-embed-v2\" is a high-performance dense embedding model\n          optimized for text retrieval and ranking tasks. It is trained on a\n          diverse range of text corpora and provides strong performance on\n          longer passages and structured documents.\n          - \"pinecone-sparse-english-v0\" is a sparse embedding model for\n          converting text to sparse vectors for keyword or hybrid search. The\n          model directly estimates the lexical importance of tokens by\n          leveraging their context.",
          "enum": [
            "multilingual-e5-large",
            "llama-text-embed-v2",
            "pinecone-sparse-english-v0"
          ],
          "type": "string"
        }
      },
      "required": [
        "model",
        "fieldMap"
      ],
      "type": "object"
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "A unique name to identify the new index.",
      "type": "string"
    },
    "region": {
      "default": "us-east-1",
      "description": "The region for the index. Common regions: aws (us-east-1, us-west-2, eu-west-1), gcp (us-central1, europe-west1), azure (eastus, westeurope). Defaults to us-east-1.",
      "type": "string"
    }
  },
  "required": [
    "name",
    "embed"
  ],
  "type": "object"
}
sha256:bdb3578001b509cec054ef02c890e2d53a27e0987984b193f9bb4b3022b1f407

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:1cf0d1eecc9678ad72a9e3a8ef7d82fe3e71154894f7f6d942e644eefff37928

Interface hash: sha256:d0b4408c39c09ca4ef8270d7235fd744825f97b4a66480434ca5dd7572ef787d

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/create-index-for-model",
  "title": "Create Index",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "create-index-for-model"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:58d355ac8daeff632db6fa83d224b5ed714adbfdb1663db437b0edf18b682673"
}
toolwrite0.3.00.4.0
describe-indexpinecone:tool:describe-index
Observed interface and hashes

Describe the configuration of a Pinecone index, including its embedding model and the "fieldMap" that names the record field holding the text to embed. Call this before upsert-records to learn the required field name. Check "status.ready" in the response to confirm the index can accept upserts and queries.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to describe.",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "type": "object"
}
sha256:436a6025bab7d21d8332405f97a62bb84638e60314635d3da852f2ae8388128f

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:a76c5da144207725bcd0124205ae466a87fa3ee5c206085d520dc443c8edc99d

Interface hash: sha256:2318d98df54611bf8ce5c097847fd3e30e82e34c8dc36ff56701a293cd5b4afb

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/describe-index",
  "title": "Describe Index",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "describe-index"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:0d8a57a4a82ecc68c7613db771f02d42a79ab8b9fa3def80f48ec0b966f52fdd"
}
toolread0.3.00.3.0
describe-index-statspinecone:tool:describe-index-stats
Observed interface and hashes

Describe the statistics of a Pinecone index, including record counts per namespace. Use this to discover which namespaces exist in an index. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to describe.",
      "type": "string"
    }
  },
  "required": [
    "name"
  ],
  "type": "object"
}
sha256:436a6025bab7d21d8332405f97a62bb84638e60314635d3da852f2ae8388128f

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5dd7826e075a67a02423b0056a48a67aeed9b215b787ae89dfb65ff9fc0872f2

Interface hash: sha256:b0ca5f18785f663126170b36d6433cbcdfad23ca30d712d8cb53bd3e4c7ef7a8

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/describe-index-stats",
  "title": "Describe Index Stats",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "describe-index-stats"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:d23433b588fecf7c3731003383809a6435fec8954ed23171b552bbfd2c65aa9f"
}
toolread0.3.00.3.0
list-indexespinecone:tool:list-indexes
Observed interface and hashes

List all Pinecone indexes in the project, including each index's configuration and readiness status. Use this to discover valid index names before calling other tools.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    }
  },
  "type": "object"
}
sha256:a889f35479a8ffa09ddcb31ce9d8335a8c4fa6cefdcb668719c687a1990435e6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:6ab7a9e38f7b0d3c65df0a3f32d541b5464984d5c06488e3a39443278d9d2ff8

Interface hash: sha256:bfa20e95b5293e161a8d48cefecad1a95d97bb6cd761f89be03a9591de9abe96

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/list-indexes",
  "title": "List Indexes",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "list-indexes"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:10a1018203c60eccad99b38c75204845ebf5a4aff934e209ea6df046690d4bb6"
}
toolread0.3.00.3.0
rerank-documentspinecone:tool:rerank-documents
Observed interface and hashes

Rerank a set of provided documents by relevance to a query. Use this for documents that did not come from a Pinecone search (e.g. externally sourced text). To rerank the results of a single-index search, prefer the "rerank" parameter of search-records instead of calling this tool separately.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "documents": {
      "description": "A set of documents to rerank. Can either be an array of text documents\n    (strings) or an array of records. Record field values must be strings;\n    records with number, boolean, or array fields are not accepted."
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "model": {
      "description": "Choose a reranking model:\n- \"cohere-rerank-3.5\" is Cohere's leading reranking model, balancing performance\nand latency for a wide range of enterprise search applications.\n- \"bge-reranker-v2-m3\" is a high-performance, multilingual reranking model that\nworks well on messy data and short queries expected to return medium-length\npassages of text (1-2 paragraphs).\n- \"pinecone-rerank-v0\" is a state of the art reranking model that out-performs\ncompetitors on widely accepted benchmarks. It can handle chunks up to 512 tokens\n(1-2 paragraphs).",
      "enum": [
        "cohere-rerank-3.5",
        "bge-reranker-v2-m3",
        "pinecone-rerank-v0"
      ],
      "type": "string"
    },
    "options": {
      "properties": {
        "rankFields": {
          "description": "The fields to rerank on. This should only be included if the documents\n        are records. The \"bge-reranker-v2-m3\" and \"pinecone-rerank-v0\" models\n        support only a single rerank field. \"cohere-rerank-3.5\" supports\n        multiple rerank fields.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "topN": {
          "description": "The number of results to return after reranking.",
          "type": "number"
        }
      },
      "required": [
        "topN"
      ],
      "type": "object"
    },
    "query": {
      "description": "The query to rerank documents against.",
      "type": "string"
    }
  },
  "required": [
    "model",
    "query",
    "documents"
  ],
  "type": "object"
}
sha256:a7010f8f08acf795f1996ed8405623c4f74d914012998b44d790377d1275e8e9

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:61b606e3c5645baee2da335196c89b894dba1b84c987880ef8c1cf9dd9cdc560

Interface hash: sha256:38e26ebf469985f930f2e2eda1180169c54f2288fec3cacd4df0b91a618000c8

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/rerank-documents",
  "title": "Rerank Documents",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "rerank-documents"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:b4ed05894ee48ab8e9840026af18dca5856f86072c862300b9f7972f707053ef"
}
toolread0.3.00.3.0
search-docspinecone:tool:search-docs
Observed interface and hashes

Search the official Pinecone documentation for relevant information. Use this before writing Pinecone code or explaining Pinecone behavior, rather than relying on assumptions.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "query": {
      "description": "The text to search for.",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "type": "object"
}
sha256:98375aa0bb0e35b7fe98b03af35cf63e6e434efb2c0b95b67b35f5fa6ab8a274

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:4dfe898c7658f0cbaacb42a02a16a482099ae1da0ccdcdc2e0b2f8de912c56fa

Interface hash: sha256:5f9072dc9b7b8fc700665d6e5f32d7cc88b43d4a7c0cf1894dfb64d22c960d29

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/search-docs",
  "title": "Search Pinecone Documentation",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "search-docs"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:cca5c0a1c07682a723c1497d885f1215cfeb1ca0f0417119e8f0ce7da8b71654"
}
toolread0.2.10.3.0
search-document-indexpinecone:tool:search-document-index
Observed interface and hashes

Search a Pinecone document index (one created with create-document-index). Call describe-index first to see which fields declare "embed", "sparseEmbed", or "fullTextSearch". Rank with one or more "scoreBy" clauses: - "embed": search by meaning on a field with "embed". Pass the query as plain text; Pinecone embeds it with the field's model. - "sparse_embed": search a field with "sparseEmbed" the same way. - "text": keyword (BM25) search on one or more full-text fields. Good for exact terms like IDs, error codes, and names. - "query_string": Lucene-style query syntax. Don't pass "fields" (the API rejects it); target fields with qualifiers inside the query, for example 'chunk_text:"exact phrase"', or omit qualifiers to search every full-text field. An "embed" or "sparse_embed" clause must be the only clause; "text" and "query_string" clauses can be combined. To rank by meaning and by exact terms, run two separate searches: their scores are on different scales, so don't compare them across searches. Returns matches with "_id", "_score", and the fields named in "includeFields". Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "filter": {
      "additionalProperties": {},
      "description": "An optional filter, such as {\"category\": {\"$eq\": \"policy\"}}. On a\n      full-text field, \"$match_phrase\", \"$match_all\", and \"$match_any\" require\n      terms, for example {\"chunk_text\": {\"$match_all\": \"refund\"}}.",
      "propertyNames": {
        "type": "string"
      },
      "type": "object"
    },
    "includeFields": {
      "default": [
        "*"
      ],
      "description": "The fields to return with each match. Defaults to [\"*\"] (all stored fields).",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to search.",
      "type": "string"
    },
    "namespace": {
      "default": "__default__",
      "description": "The namespace to search. Defaults to \"__default__\".",
      "type": "string"
    },
    "scoreBy": {
      "description": "The clauses that rank the documents.",
      "items": {
        "description": "A scoring clause.",
        "properties": {
          "fields": {
            "description": "The fields to score. \"embed\" and \"sparse_embed\" take exactly one; \"text\" takes one or more. Omit for \"query_string\", which rejects it.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "query": {
            "description": "The query text.",
            "type": "string"
          },
          "type": {
            "description": "The scoring method.",
            "enum": [
              "embed",
              "sparse_embed",
              "text",
              "query_string"
            ],
            "type": "string"
          }
        },
        "required": [
          "type",
          "query"
        ],
        "type": "object"
      },
      "minItems": 1,
      "type": "array"
    },
    "topK": {
      "default": 10,
      "description": "The number of matches to return. Defaults to 10.",
      "maximum": 9007199254740991,
      "minimum": 1,
      "type": "integer"
    }
  },
  "required": [
    "name",
    "scoreBy"
  ],
  "type": "object"
}
sha256:f72f2bdb6ea007a98a32c5151bd50687d3cf25619bb2b12f3e1005d3c480ac11

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5e895a08e85a4e7787f801cdd7f6c1ba3bbab1895558bbb3099ba5de5877c85b

Interface hash: sha256:252c4a637b52bf860c65f46725b8b76004aedbb4071624f8e9392bc207f6ad1d

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/search-document-index",
  "title": "Search Document Index",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "search-document-index"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:e882bddaa89c83b78252f48171c0549a07c31b1bfa84a3bb4ac6ef10e305c52a"
}
toolread0.4.00.4.0
search-recordspinecone:tool:search-records
Observed interface and hashes

Search an index for records that are semantically similar to the query text. Only works with integrated-inference indexes (e.g. created with create-index-for-model), which embed the query automatically; it fails on standard indexes and document indexes (use search-document-index for those) — use describe-index to check the index type. Returns hits with "_id", "_score", and the record's stored "fields". Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to search.",
      "type": "string"
    },
    "namespace": {
      "description": "The namespace to search.",
      "type": "string"
    },
    "query": {
      "description": "A query to search for records.",
      "properties": {
        "filter": {
          "additionalProperties": {},
          "description": "A filter can be used to narrow down results. Use the syntax of\n        MongoDB's query and projection operators: $eq, $ne, $gt, $gte, $lt,\n        $lte, $in, $nin, $exists, $and, $or. Make sure the records in the index\n        contain the fields that you are filtering on. To discover which fields\n        exist, run a search without a filter and inspect the \"fields\" of the\n        returned hits. Filtering on a field that records do not contain\n        returns no results.",
          "properties": {},
          "type": "object"
        },
        "inputs": {
          "properties": {
            "text": {
              "description": "The text to search for.",
              "type": "string"
            }
          },
          "required": [
            "text"
          ],
          "type": "object"
        },
        "topK": {
          "description": "The number of results to return. 10 is a reasonable default; use a\n      larger value (e.g. 50) when reranking, so the reranker has more\n      candidates to choose from. Very large values increase latency and\n      response size.",
          "type": "number"
        }
      },
      "required": [
        "topK",
        "inputs"
      ],
      "type": "object"
    },
    "rerank": {
      "description": "Reranking can help determine which of the returned records are most\n  relevant. When reranking, use a \"query\" with a \"topK\" that returns more\n  results than you need; then use \"rerank\" to select the most relevant\n  \"topN\" results.",
      "properties": {
        "model": {
          "description": "Choose a reranking model:\n- \"cohere-rerank-3.5\" is Cohere's leading reranking model, balancing performance\nand latency for a wide range of enterprise search applications.\n- \"bge-reranker-v2-m3\" is a high-performance, multilingual reranking model that\nworks well on messy data and short queries expected to return medium-length\npassages of text (1-2 paragraphs).\n- \"pinecone-rerank-v0\" is a state of the art reranking model that out-performs\ncompetitors on widely accepted benchmarks. It can handle chunks up to 512 tokens\n(1-2 paragraphs).",
          "enum": [
            "cohere-rerank-3.5",
            "bge-reranker-v2-m3",
            "pinecone-rerank-v0"
          ],
          "type": "string"
        },
        "query": {
          "description": "An optional query to rerank documents against. If not specified, the\n      same query will be used for both the initial search and the reranking.",
          "type": "string"
        },
        "rankFields": {
          "description": "The fields to rerank on. This should include the field name specified\n    in the index's \"fieldMap\". The \"bge-reranker-v2-m3\" and\n    \"pinecone-rerank-v0\" models support only a single rerank field.\n    \"cohere-rerank-3.5\" supports multiple rerank fields.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "topN": {
          "description": "The number of results to return after reranking. Must be less than or\n      equal to the value of \"query.topK\".",
          "type": "number"
        }
      },
      "required": [
        "model",
        "rankFields"
      ],
      "type": "object"
    }
  },
  "required": [
    "name",
    "namespace",
    "query"
  ],
  "type": "object"
}
sha256:c5e4b64c08d54c9c93a2fff2f579c634ffaf851b72bb7820cf478895bcf7a7c6

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:7f58ba99fdb1bbb71efbec9e0b5224322044643a5e0ec9e4f36a0b85d4d6c57a

Interface hash: sha256:70bdaa9cebf9e752fac5a51c390b025b868a3f63d6854c999da1daa323e1603e

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/search-records",
  "title": "Search Records",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "search-records"
  },
  "declared": {
    "read_only": "true",
    "destructive": "unknown",
    "idempotent": "false",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:7c430bce47d96d33cda56d1bb5eb60a80a3ffac880e78720b70133e0da0b33d8"
}
toolread0.3.00.4.0
upsert-documentspinecone:tool:upsert-documents
Observed interface and hashes

Insert or update documents in a Pinecone document index (one created with create-document-index). Each document needs an "_id" and plain text in every field the index declares with "embed"; Pinecone embeds that text on write, so never send vectors. Call describe-index first to see the schema. Fields not in the schema are stored as metadata you can filter on. Documents with an existing "_id" are replaced. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "documents": {
      "description": "The documents to upsert. Larger sets are sent in batches of 96.",
      "items": {
        "additionalProperties": {
          "description": "A field value. Must be a string, number, boolean, or array of strings."
        },
        "description": "A document to upsert. Must have an \"_id\" field and plain text in each field\n    the index declares with \"embed\".",
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "minItems": 1,
      "type": "array"
    },
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to upsert into.",
      "type": "string"
    },
    "namespace": {
      "default": "__default__",
      "description": "The namespace to upsert into. Defaults to \"__default__\".",
      "type": "string"
    }
  },
  "required": [
    "name",
    "documents"
  ],
  "type": "object"
}
sha256:e09710ba195472b3571884bf673ca81d4254273173f0ccf161f50e3e7f5c29fa

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:5f30e0f76789f59c39b74c36ce58ca92ab71ee6866255b2aa200434bf0c317e2

Interface hash: sha256:f1317e9e98fc305c763814b5c973e9cd6991c6f2b58cb1a3d9f3d6f61582845e

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/upsert-documents",
  "title": "Upsert Documents",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "upsert-documents"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "unknown"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:8211e147c1f2a6fff40456991cedb1c57cbf3f3ed982f6b55881c897c71699fc"
}
tooldestructive0.4.00.4.0
upsert-recordspinecone:tool:upsert-records
Observed interface and hashes

Insert or update records in an integrated Pinecone index. For a document index, use upsert-documents instead. Text in the field named by the index's "fieldMap" is embedded automatically — call describe-index first to confirm that field name. Records with an existing "id" are overwritten. Newly upserted records can take a few seconds to be indexed and become visible to search results and index stats; if recent data is missing, wait briefly and retry.

Input schema

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "llm_model": {
      "description": "Optional. If you are an AI model, use this field to specify your name (e.g., \"gpt-4o\", \"Composer\", \"Claude Sonnet 4\", \"Claude Opus\", \"Gemini 2.5\", \"Cascade\", \"Grok 4.1\", \"Copilot\", \"Devin\", and many others). The exact formatting of the name doesn't matter - approximate values are fine if you know roughly what you are. Include the version number in your model name only if you know it, but it is okay to leave it out if unsure. If you don't know your model name, omit this field entirely.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "llm_provider": {
      "description": "Optional. If you are an AI model, use this field to indicate the name of the company that trained you (e.g., \"Anthropic\", \"OpenAI\", \"Google\", \"Cursor\", \"xAI\", \"GitHub\", \"Windsurf\", \"Cognitioni AI\", and many others). The exact formatting doesn't matter - approximate values are fine. If you don't know your provider, avoid guessing and omit this field.  **Do not prompt the user for this.** This value is used to track usage analytics. ",
      "type": "string"
    },
    "name": {
      "description": "The index to upsert into.",
      "type": "string"
    },
    "namespace": {
      "description": "The namespace to upsert into.",
      "type": "string"
    },
    "records": {
      "description": "A set of records to upsert into the index. Use a consistent schema for all\n  records in the index.",
      "items": {
        "additionalProperties": {
          "description": "A field value. Must be a string, number, boolean, or array of strings."
        },
        "description": "A record to upsert. Must have an \"id\" or \"_id\" field and contain text in\n    the field specified by the index's \"fieldMap\".",
        "propertyNames": {
          "type": "string"
        },
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "name",
    "namespace",
    "records"
  ],
  "type": "object"
}
sha256:2da74df95cfe3cf04a4d40bd900864b99cf60ab81b71d9899f19eac9246f3b8b

Output schema

Not exposed in the analyzed interface.

sha256:398b676e47d03a29016ee92fe378b8b4f1b3e965390c4c64ce78d27f79df74d1

Description hash: sha256:9c5ba3b554aeddc2c19fbe4eacce31222231ffc734fcc87b3e61a4f23b639d2d

Interface hash: sha256:8704f0352119ba3ec97320064924e19eb9cce95ab90ab0277c9dc440d7b309ac

Other observed Modelara metadata
{
  "id": "mcp:pinecone-mcp/upsert-records",
  "title": "Upsert Records",
  "source": {
    "type": "mcp",
    "server": "pinecone-mcp",
    "operation": "upsert-records"
  },
  "declared": {
    "read_only": "false",
    "destructive": "true",
    "idempotent": "true",
    "open_world": "unknown"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "unknown"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:3e24c3fd770ff2203cde752058fbd1295d89d7dd4e6c01f5675ef50371d8c785"
}
tooldestructive0.3.00.4.0

STATIC COMPARISONS

Release history

2 release transitions
  1. 3 added0 removed0 schema1 write1 destructive0 unknown

    Nov 15, 2026· Pending human review

  2. 8 added0 removed0 schema1 write1 destructive0 unknown

    Nov 15, 2026· Pending human review