data Static interface comparison
Pinecone MCP
0.3.0 0.4.0
1 new write capability requires explicit review.1 new destructive capability requires explicit review.
View the upgrade review as Markdown
A shareable summary of this comparison for an issue, pull request or ticket. Select the text and copy it.
INTERFACE DIFF
What changed, tool by tool
- 3Added tools
- 0Removed tools
- 3Modified tools
- 0Input-schema changes
- 0Output-schema changes
- 2Declared authority changes
6 tools with recorded changes
create-document-indexAddedWhat changed
- New tool create-document-index, declared with write effect.
Why it could matter
- Agents connected to this release can be offered an operation that changes data, which the earlier release did not expose.
What to verify
- Review whether this operation should be exposed through your agent’s tool configuration.
- Declared effect
- — → write
Input schema
Property Previous (0.3.0) Current (0.4.0) Change (schema root)not present object - Added
cloudnot present string, default="aws", enum (3)optional - Added
fieldsnot present object, additionalProperties {…}, propertyNames {…}required - Added
llm_modelnot present stringoptional - Added
llm_providernot present stringoptional - Added
namenot present stringrequired - Added
regionnot present string, default="us-east-1"optional - Added
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
create-index-for-modelModifiedWhat changed
- create-index-for-model: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- write → write
- Description
- PreviousCreate 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.
- CurrentCreate 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
Input schema unchanged.
10 unchanged entries
(schema root)cloudembedembed › fieldMapembed › fieldMap › textembed › modelllm_modelllm_providernameregion
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
search-document-indexAddedWhat changed
- New read-only tool search-document-index.
Why it could matter
- The release adds a capability without declared write authority.
What to verify
- Decide whether agents should be offered this tool.
- Declared effect
- — → read
Input schema
Property Previous (0.3.0) Current (0.4.0) Change (schema root)not present object - Added
filternot present object, additionalProperties {…}, propertyNames {…}optional - Added
includeFieldsnot present array, default (1)optional - Added
includeFields › [items]not present string - Added
llm_modelnot present stringoptional - Added
llm_providernot present stringoptional - Added
namenot present stringrequired - Added
namespacenot present string, default="__default__"optional - Added
scoreBynot present array, minItems=1required - Added
scoreBy › [items]not present object - Added
scoreBy › [items] › fieldsnot present arrayoptional - Added
scoreBy › [items] › fields › [items]not present string - Added
scoreBy › [items] › querynot present stringrequired - Added
scoreBy › [items] › typenot present string, enum (4)required - Added
topKnot present integer, default=10, maximum=9007199254740991, minimum=1optional - Added
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
search-recordsModifiedWhat changed
- search-records: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- read → read
- Description
- PreviousSearch 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 — 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.
- CurrentSearch 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
Input schema unchanged.
16 unchanged entries
(schema root)llm_modelllm_providernamenamespacequeryquery › filterquery › inputsquery › inputs › textquery › topKrerankrerank › modelrerank › queryrerank › rankFieldsrerank › rankFields › [items]rerank › topN
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
upsert-documentsAddedWhat changed
- New tool upsert-documents, declared with destructive effect.
Why it could matter
- Agents connected to this release can be offered an operation declared as able to delete or irreversibly change data.
What to verify
- Review whether this operation should be exposed to agents, and whether it should require explicit approval.
- Declared effect
- — → write
Input schema
Property Previous (0.3.0) Current (0.4.0) Change (schema root)not present object - Added
documentsnot present array, minItems=1required - Added
documents › [items]not present object, additionalProperties {…}, propertyNames {…} - Added
llm_modelnot present stringoptional - Added
llm_providernot present stringoptional - Added
namenot present stringrequired - Added
namespacenot present string, default="__default__"optional - Added
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
upsert-recordsModifiedWhat changed
- upsert-records: description changed.
Why it could matter
- Models choose and call tools partly from their descriptions.
What to verify
- Spot-check that agents still select this tool as intended.
- Declared effect
- write → write
- Description
- PreviousInsert or update records in an integrated Pinecone index. 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.
- CurrentInsert 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
Input schema unchanged.
7 unchanged entries
(schema root)llm_modelllm_providernamenamespacerecordsrecords › [items]
No output schema is recorded for this tool in either release.
Link to this toolExact JSON from the published snapshots
Loads the exact recorded definitions of this tool from both releases. The full snapshots are linked under Evidence and provenance.
No tools match these filters.
6 tools with no recorded change
cascading-searchdescribe-indexdescribe-index-statslist-indexesrerank-documentssearch-docs
Evidence and provenance
- Static findings
- FAIL from Modelara’s automated analysis of the two declared interfaces. A policy outcome, not a security rating or a runtime test.
- Human review
- Pending human review. No reviewer decision is recorded for this comparison.
- Published evidence
- Part of Valyd’s published data generation listed in valyd-data-source.json. Published records are not rewritten.
Show provenance and exact files
- Comparison
pinecone/0.3.0~0.4.0The published comparison identifier.- Analyzer
modelara v0.1.8Policy version not recorded.Analyzed Nov 15, 2026, 3:10 AM UTC.- Distribution
npm- Previous release
@pinecone-database/mcp@0.3.09 tools · published by the registry Aug 7, 2026, 3:38 PM UTCArtifact integritysha512-hC8nc4VgNi6wbXkergDP3q/8zHnhx67HtuL/lNPtvnlfCmIGNTMEYXX6hkWvvqhHliDTwK+Y8PnIHR3IBRkSVw==Interface fingerprintsha256:7db05adbc00fd3a8defeb737029984bf1564018031d3b8585a523c1dc89f8195Exact interface snapshot (JSON)- Current release
@pinecone-database/mcp@0.4.012 tools · published by the registry Oct 29, 2026, 5:28 PM UTCArtifact integritysha512-JewEAQw+C3vys9hWT4vMePzeP5AA8QZeHMmS4JPtYIuHZtdQRmx0o4DZZCcdXluT8dNEXM3oh1tB473vJgUA8A==Interface fingerprintsha256:a38bfd1ec11bab5f5320081e92a67819117d9c40532a380e332575e6f9120910Exact interface snapshot (JSON)- Comparison record
- Exact comparison record (JSON)
The integrity value or digest identifies the exact artifact that was inspected; it does not show that the package is safe. The interface fingerprint identifies the declared tools and schemas Modelara recorded for that release.
MODELARA ANALYSIS OUTPUT
Interface findings
Policy failures
2 findingscreate-document-indexFAILAddedupsert-documentsFAILAdded
Informational
4 findingssearch-document-indexINFOAddedcreate-index-for-modelINFOChangedsearch-recordsINFOChangedupsert-recordsINFOChanged
What do these results mean?
- PASS
- No policy-significant interface change detected.
- REVIEW
- Interface changes require inspection.
- FAIL
- A policy-significant change was detected.
- INVALID
- The comparison could not be evaluated reliably.