Skip to main content
Glama
linxule

MinerU MCP Server

by linxule
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

mineru_batch

Parse up to 200 document URLs in a single batch to extract content, using public URLs for faster and more reliable processing.

Instructions

Parse multiple URLs in one batch (max 200). Preferred over mineru_upload_batch — faster and more reliable. Use public URLs (arXiv, SSRN, publisher sites) when available.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ocrNoEnable OCR (pipeline only)
urlsYesArray of document URLs, or a single URL string
modelNopipeline=fast, vlm=90% accuracy
tableNoTable recognition
formatsNoExtra export formats
formulaNoFormula recognition
languageNoLanguage code: ch, en, etc

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv1.1.6
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / urls / anyOf
      Added value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "string"
+  }
+]
    • changedInput schema / properties / urls / description
      Previous value: -"Array of document URLs"New value: +"Array of document URLs, or a single URL string"
    • removedInput schema / properties / urls / items
      Removed value: -{
-  "type": "string"
-}
    • removedInput schema / properties / urls / type
      Removed value: -"array"
  2. First observedv1.0.0

TDQS

A3.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral disclosure burden, but it only adds a max batch size and a comparative reliability claim. It does not disclose whether this is an asynchronous job submission, what the response contains, how to track progress, or how to retrieve results, even though sibling tool names like mineru_batch_status and mineru_download_results imply such a workflow.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with the core action and limit front-loaded. Every clause earns its place: the batch limit, the preferred-alternative note, and the public-URL guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter tool with no output schema and no annotations, the description under-specifies the call flow: it doesn't mention job submission, status polling, result download, or how the model/formats/ocr options relate to the batch behavior. An agent would have to infer the asynchronous workflow purely from sibling tool names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description adds the 'max 200' constraint on the urls parameter, which is not present in the schema. It also connects 'batch' to multiple URLs, providing a small but useful semantic addition beyond the raw property descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific action and object: 'Parse multiple URLs in one batch,' and adds a concrete limit of max 200. It also explicitly distinguishes itself from the closest sibling, mineru_upload_batch, by noting it is preferred and faster/more reliable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names mineru_upload_batch as the alternative and states when this tool should be preferred, including a speed/reliability rationale and a recommendation to use public URLs. However, it never states when not to use this tool relative to other siblings such as mineru_parse or mineru_parse_long, and it doesn't cover limits beyond the max 200 hint.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools