Skip to main content
Glama
enesjakozh
ai-zerolab

pymupdf4llm-mcp

by ai-zerolab
OverviewSchemaRelated ServersScoreDiscussions
Python

This package has been merged into official repo, please use the official repo instead.

https://github.com/pymupdf/pymupdf4llm-mcp

pymupdf4llm-mcp

Release Build status codecov Commit activity License

MCP Server for pymupdf4llm, best for export PDF to markdown for LLM.

Quick Start

Run the following command to run the MCP server:

uvx pymupdf4llm-mcp@latest stdio # stdio mode
# or
uvx pymupdf4llm-mcp@latest sse # sse mode

Configure your cursor/windsurf/... and other MCP client to this server:

{
  "mcpServers": {
    "pymupdf4llm-mcp": {
      "command": "uvx",
      "args": [
        "pymupdf4llm-mcp@latest",
        "stdio"
      ],
      "env": {}
    }
  }
}

Available Tools

1 tool
convert_pdf_to_markdownA

Converts a PDF file to markdown format via pymupdf4llm. See pymupdf.readthedocs.io/en/latest/pymupdf4llm for more. The file_path, image_path, and save_path parameters should be the absolute path to the PDF file, not a relative path. This tool will also convert the PDF to images and save them in the image_path directory. For larger PDF files, use save_path to save the markdown file then read it partially.

ParametersJSON Schema
NameRequiredDescriptionDefault
file_pathYesAbsolute path to the PDF file to convert
image_pathNoOptional. Absolute path to the directory to save the images. If not provided, the images will be saved in the same directory as the PDF file.
save_pathNoOptional. Absolute path to the directory to save the markdown file. If provided, will return the path to the markdown file. If not provided, will return the markdown string.

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description must carry the transparency burden. It discloses that the tool also converts PDF to images and saves them, and that absolute paths are required. However, it does not mention side effects (e.g., overwriting existing files), error handling, or permissions. It provides adequate but not comprehensive behavioral insight.

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

Conciseness4/5

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

The description is fairly concise with 3-4 sentences. It front-loads the main purpose and then provides details. The full URL is slightly lengthy but appropriate for reference. It earns its sentences.

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

Completeness4/5

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

Given the presence of an output schema (context signal), the description covers the essential conversion behavior, image generation, and practical usage tips for large files. It does not address edge cases like encrypted PDFs or invalid paths, but is sufficient for typical use.

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 each parameter has a description. The description reinforces the absolute path requirement and adds context: image_path is optional with default behavior, save_path controls whether output is a string or file path, and advice for large files. This adds value beyond the schema.

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 clearly states the tool converts a PDF file to markdown format using a specific library (pymupdf4llm). It specifies the verb 'converts' and the resource 'PDF file to markdown', and also mentions additional behavior like converting to images. With no sibling tools, it is unambiguous.

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?

The description provides explicit guidance: use absolute paths for all parameters, and for larger PDF files use save_path to save the markdown file and read it partially. It does not discuss alternatives (none exist) but gives practical usage context.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 1 tool update
    • First observedconvert_pdf_to_markdown
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity. The tool's purpose is clearly described, and an agent will have no difficulty selecting it.

Naming Consistency5/5

The single tool name follows a consistent verb_noun pattern in snake_case. There are no other tools to introduce inconsistency.

Tool Count3/5

The server has only one tool, which feels thin for a PDF conversion service. While it covers the core conversion task, a slightly richer set (e.g., 3-5 tools) would be more appropriate.

Completeness2/5

The tool converts PDF to markdown with optional image extraction, but lacks other common operations like text extraction without conversion, page range selection, or batch processing. Significant gaps exist.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ai-zerolab/pymupdf4llm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server