Developer-tools MCP server

MinerU Open MCP

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

View watchlist

DistributionDistribution: PyPI
Packagemineru-open-mcp
Latest analyzed version1.0.22
Current tool count2
Latest analysisNov 17, 2026
Package source

OBSERVED INTERFACE

Capability surface

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

3 releases analyzed1.0.20 → 1.0.22Latest: 1.0.22
  • read1
  • write1
  • destructive0
  • 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
mineru-open-mcp@1.0.22
Registry
pypi
Published
Sep 22, 2026
Integrity
sha256-HLy6Qy9DvTiKQNzRtFPoWhn1ErX3WNYh5SyPAllKgEQ=
Analyzer
modelara v0.1.8 · policy not recorded

2 capabilities

CapabilityTypeDerived effectFirst observed in Valyd coverageLast changed
get_ocr_languagesopendatalab-mineru-open-mcp:tool:get_ocr_languages
Observed interface and hashes

Return supported MinerU OCR and script language codes (e.g. ch, en, japan, latin). Read-only; no uploads. Use before setting the language argument on parse_documents for scanned or multilingual documents. Do not use for file conversion; call parse_documents instead.

Input schema

{
  "additionalProperties": false,
  "properties": {},
  "type": "object"
}
sha256:fc182e1a69a66dadc6c6ee98df9606d1d4fd90fb51b082083aaa8c230cb4765c

Output schema

{
  "additionalProperties": true,
  "type": "object"
}
sha256:7751ca245b89acd7d145f5c7b68cb80458b8d38bfe36a965a332f56bc2525a8c

Description hash: sha256:89e9e741f4286f0b83ef8b531077a8b8ecf621410d3c131ee18d5ba96c691409

Interface hash: sha256:e976cd30a350e8a28eebd6745f411609fd162f5e6971ef491a8ab0064eea6d48

Other observed Modelara metadata
{
  "id": "mcp:MinerU — SOTA PDF & Document Parser for AI Workflows/get_ocr_languages",
  "title": "List OCR language codes",
  "source": {
    "type": "mcp",
    "server": "MinerU — SOTA PDF & Document Parser for AI Workflows",
    "operation": "get_ocr_languages"
  },
  "declared": {
    "read_only": "true",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "false"
  },
  "safety": {
    "idempotent": "true",
    "retry_safe": "true"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:932b7d2a3be2567c3ac5b2137d69a8e1cb758b1455dbc1005eb1961cf45afed2"
}
toolread1.0.201.0.22
parse_documentsopendatalab-mineru-open-mcp:tool:parse_documents
Observed interface and hashes

Convert PDF, Office (DOCX, PPTX), spreadsheets (XLSX in Flash mode), images, and http(s) URLs to Markdown using the MinerU cloud API (content is uploaded to mineru.net; do not use for data that must stay on-device). Does not modify source files; may write Markdown under output_dir when saving results. Auth: without MINERU_API_TOKEN, Flash mode applies (Markdown-only, about 20 pages and 10 MB per file; service rate limits). With MINERU_API_TOKEN, higher limits and optional formats per plan. Use for extraction and conversion. Use get_ocr_languages only to list OCR language codes, not to parse files. Not for fully offline parsing. Parameters: file_sources is paths/URLs or objects with source and pages for PDF ranges; language is an OCR code (default ch); enable_ocr defaults to auto (null); set model to html only if every source is a web page URL.

Input schema

{
  "additionalProperties": false,
  "properties": {
    "enable_ocr": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "OCR mode:\n  null (default) - auto-detect: the server decides whether OCR is needed.\n  true           - force OCR on when the user mentions poor scan quality.\n  false          - disable OCR.\nOmit this parameter unless the user explicitly mentions scan quality issues."
    },
    "file_sources": {
      "description": "Files to parse. Each entry is either:\n  - a plain string: a local file path or URL\n  - a dict {\"source\": \"...\", \"pages\": \"N-M\"}: with an optional page range\nPage range: \"N\" (single page) or \"N-M\" (for example \"1-10\"). PDF only. Duplicate sources are allowed, for example the same PDF with different ranges.\nExamples:\n  [\"report.pdf\"]\n  [{\"source\": \"report.pdf\", \"pages\": \"1-5\"}]\n  [{\"source\": \"a.pdf\", \"pages\": \"1-3\"}, {\"source\": \"a.pdf\", \"pages\": \"10-15\"}]\n  [\"https://example.com/doc.pdf\", \"local.docx\"]",
      "items": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "additionalProperties": {
              "type": "string"
            },
            "type": "object"
          }
        ]
      },
      "type": "array"
    },
    "language": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "OCR language code. Omit if unknown; the server defaults to \"ch\" (Chinese + English). Infer from the document filename when possible, for example \"manual_en.pdf\" -> \"en\". Common codes: \"ch\", \"en\", \"japan\", \"korean\", \"latin\", \"arabic\", \"cyrillic\", \"devanagari\". Full list: call get_ocr_languages."
    },
    "model": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Parsing model. Set to \"html\" only when all file_sources are web page URLs. Otherwise omit it and let MinerU auto-select the appropriate model. Ignored in Flash mode."
    },
    "output_dir": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Directory used when parsed results need to be saved locally, such as batch parsing or oversized inline content. Defaults to the server-configured directory."
    }
  },
  "required": [
    "file_sources"
  ],
  "type": "object"
}
sha256:e36510a126c06a05dd4dc8331c2407eb47f2ebbb35147cb5975c965dbc48ac98

Output schema

{
  "additionalProperties": true,
  "type": "object"
}
sha256:7751ca245b89acd7d145f5c7b68cb80458b8d38bfe36a965a332f56bc2525a8c

Description hash: sha256:fd8478da7c225bf7312909eca7931e6a3e2d57c0d247283fab21289f734cf8ce

Interface hash: sha256:5943d5f7a31b3c3550135b906f2481d3bc3e7b5a56429b118bf2cf31bff3891e

Other observed Modelara metadata
{
  "id": "mcp:MinerU — SOTA PDF & Document Parser for AI Workflows/parse_documents",
  "title": "Parse documents to Markdown",
  "source": {
    "type": "mcp",
    "server": "MinerU — SOTA PDF & Document Parser for AI Workflows",
    "operation": "parse_documents"
  },
  "declared": {
    "read_only": "false",
    "destructive": "false",
    "idempotent": "false",
    "open_world": "true"
  },
  "safety": {
    "idempotent": "false",
    "retry_safe": "false"
  },
  "metadata": {
    "mcp.annotations": "present"
  },
  "fingerprint": "sha256:59a5aa3d907ff3714dfb7305e2e1bf8666b56e2ecbd1fa996ee75661c11e73f3"
}
toolwrite1.0.201.0.22

STATIC COMPARISONS

Release history

2 release transitions
  1. 0 added0 removed0 schema1 write0 destructive0 unknown

    Nov 17, 2026· Pending human review

  2. 0 added0 removed0 schema0 write0 destructive0 unknown

    Nov 17, 2026· Automated static analysis