Skip to main content
Glama
protagolabs

NetMind ParsePro

by protagolabs
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

NetMind ParsePro

The PDF Parser AI service, built and customized by the NetMind team, is a high-quality, robust, and cost-efficient solution for converting PDF files into specified output formats such as JSON and Markdown. It is fully MCP server–ready, allowing seamless integration with AI agents.

Components

Tools

  • parse_pdf: Parses a PDF file and returns the extracted content in the specified format. The tools supports both local file paths and remote URLs as input sources. It extracts the content from the PDF and formats it either as structured JSON or as a Markdown string.

    • source: required: The source of the PDF file to be parsed.

      • If it is a string starting with "http://" or "https://", it will be treated as a remote URL.

      • Otherwise, it will be treated as a local file path (absolute path recommended, e.g. "/Users/yourname/file.pdf").

    • format: the desired format for the parsed output. Supports: "json", "markdown"

    • Returns the extracted content in the specified format (JSON dictionary or Markdown string).

Related MCP server: MCP-PDF2MD

Installation

Requires UV (Fast Python package and project manager)

If uv isn't installed.

# Using Homebrew on macOS
brew install uv

or

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Environment Variables

You can obtain an API key from Netmind

  • NETMIND_API_TOKEN: Your Netmind API key

Cursor & Claude Desktop && Windsurf Installation

Add this tool as a mcp server by editing the Cursor/Claude/Windsurf config file.

{
  "mcpServers": {
    "parse-pdf": {
      "env": {
        "NETMIND_API_TOKEN": "XXXXXXXXXXXXXXXXXXXX"
      },
      "command": "uvx",
      "args": [
        "netmind-parse-pdf-mcp"
      ]
    }
  }
}

Cursor

  • On MacOS: /Users/your-username/.cursor/mcp.json

  • On Windows: C:\Users\your-username\.cursor\mcp.json

Claude

  • On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

  • On Windows: %APPDATA%/Claude/claude_desktop_config.json

Windsurf

  • On MacOS: /Users/your-username/.codeium/windsurf/mcp_config.json

  • On Windows: C:\Users\your-username\.codeium\windsurf\mcp_config.json

Available Tools

1 tool
parse_pdfA
Parses a PDF file and returns the extracted content in the specified format.

The function supports both local file paths and remote URLs as input sources. It extracts
the content from the PDF and formats it either as structured JSON or as a Markdown string.

:param source: The source of the PDF file to be parsed.
    - If it is a string starting with "http://" or "https://", it will be treated as a remote URL.
    - Otherwise, it will be treated as a local file path (absolute path recommended, e.g. "/Users/yourname/file.pdf").
:param format: The desired format for the parsed output. Supports:
    - "json": Returns the extracted content as a dictionary.
    - "markdown": Returns the extracted content as a Markdown-formatted string.
:return: The extracted content in the specified format (JSON dictionary or Markdown string).
ParametersJSON Schema
NameRequiredDescriptionDefault
sourceYes
formatNojson

TDQS

A4.3/5.0
Behavior3/5

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

No annotations are provided, so the description must carry the full behavioral burden. It describes basic functionality (content extraction, format options) but does not mention limitations like password-protected PDFs, file size limits, or error handling. This is adequate but not thorough.

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 appropriately sized and front-loaded with the main purpose. However, it uses a docstring style with 'param' and 'return' labels, which adds some verbosity but remains clear and organized.

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

Completeness3/5

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

Given no output schema, the description explains the return type (JSON dictionary or Markdown string) but lacks detail on the structure of the JSON or the content of the Markdown. It also does not cover edge cases or error scenarios, leaving some gaps.

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

Parameters5/5

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

Schema description coverage is 0%, but the description adds significant meaning to both parameters. For 'source', it explains URL vs local file detection; for 'format', it clarifies allowed values and return types. This fully compensates for the schema's lack of 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 clearly states the tool parses a PDF and returns extracted content in specified format. It uses specific verb 'parse' and resource 'PDF', and there are no sibling tools, so differentiation is not an issue.

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

Usage Guidelines5/5

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

The description explicitly explains when to use the tool and how to specify the source (local path vs URL via 'http' or 'https' prefix). It provides clear context on input types, which is comprehensive.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

The tool name 'parse_pdf' follows a clear verb_noun pattern, which is consistent. Since it's the only tool, the naming is perfectly consistent.

Tool Count3/5

With only one tool, the server is minimal. While it serves a focused purpose (PDF parsing), a single tool feels thin compared to typical servers that offer multiple operations. It is borderline appropriate.

Completeness5/5

The tool covers the essential functionality of parsing a PDF and returning content in two common formats. For a dedicated PDF parser, this is complete. No obvious missing features like page range filtering or OCR are required for basic usage.

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

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/protagolabs/Netmind-Parse-PDF-MCP'

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