Skip to main content
Glama
Sign In
enesjakozh
mcp-pdf-tools

mcp-pdf-tools

by hanweg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

WORK IN PROGRESS - USE WITH CAUTION - Windows:

MCP PDF Tools Server

An MCP (Model Context Protocol) server that provides PDF manipulation tools. This server allows LLMs to perform operations like merging PDFs and extracting pages through the Model Context Protocol.

Features

  • Merge multiple PDF files into a single PDF

  • Merge multiple PDF files into a single PDF in user specified order

  • Extract specific pages from a PDF file

  • Search PDFs filesystem search or Everything search works better than this

  • Find (and merge) related PDFs based on text extraction and regex pattern matching from a target input PDF

Related MCP server: oxidize-pdf

Installation

  1. Clone this repository

cd mcp-pdf-tools

# Create and activate virtual environment
uv venv
.venv\Scripts\activate

# Install the package
uv pip install -e .

Usage with Claude Desktop

Add this to your Claude Desktop configuration file (claude_desktop_config.json):

{
    "mcpServers": {
        "pdf-tools": {
            "command": "uv",
            "args": [
                "--directory",
                "PATH_TO\\mcp-pdf-tools",
                "run",
                "pdf-tools"
            ],
            "env": {
                "PDF_TOOLS_ALLOWED_DIRS": "PATH_TO\\shared\\pdfs"
            }
        }
    }
}

PDF_TOOLS_ALLOWED_DIRS is an optional path list (use your OS path separator) that restricts file access for all tools. If not set, the server limits access to its current working directory.

Write tools (merge-pdfs, extract-pages, merge-pdfs-ordered) refuse to overwrite an existing output file unless overwrite: true is provided.

Available Tools

5 tools
extract-pagesB

Extract specific pages from a PDF file

Inputs: input_path (required), output_path (required), pages (required).

find-related-pdfsC

Find a PDF and then search for related PDFs based on its content, including common substring patterns

Inputs: base_path (required), target_filename (required), pattern_matching_only, min_pattern_occurrences.

merge-pdfsC

Merge multiple PDF files into a single PDF

Inputs: input_paths (required), output_path (required).

merge-pdfs-orderedB

Merge PDFs in a specific order based on patterns or exact names

Inputs: base_path (required), patterns (required), output_path (required), fuzzy_matching.

search-pdfsC

Search for PDF files in a directory with optional pattern matching

Inputs: base_path (required), pattern, recursive.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 5 tools

    Disambiguation3/5

    There is some overlap between tools like 'merge-pdfs' and 'merge-pdfs-ordered', which could cause confusion as both handle merging but with different ordering approaches. However, other tools like 'extract-pages' and 'search-pdfs' have distinct purposes, and descriptions help clarify the differences between merging variants.

    Naming Consistency5/5

    All tool names follow a consistent verb-noun pattern with hyphen separation (e.g., 'extract-pages', 'merge-pdfs'), making them predictable and readable. There are no deviations in naming conventions across the set.

    Tool Count5/5

    With 5 tools, this server is well-scoped for PDF manipulation tasks, covering extraction, merging, and searching without being overly complex or too sparse. Each tool appears to serve a specific and necessary function in the domain.

    Completeness4/5

    The tool set covers key PDF operations like extraction, merging, and searching, with 'find-related-pdfs' adding a unique content-based feature. A minor gap is the lack of tools for PDF creation or editing (e.g., adding text or images), but core workflows are adequately supported for a focused PDF utility server.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • oxidize-pdf

      bzsanti
      A
      license
      A
      quality
      B
      maintenance
      Rust-powered PDF toolkit over MCP: create, read, and analyze PDFs; extract text and entities for RAG; convert to Markdown; split/merge/rotate/reorder pages; manage form fields and annotations; encrypt documents. Runs locally via uvx oxidize-mcp.
      12
      1,289 PyPI
      6
      MIT

    • pdf-automation

      Feynman520
      A
      license
      Not graded
      quality
      C
      maintenance
      A local MCP server that drives PDFium and pypdf to perform comprehensive PDF operations including inspection, assembly, page editing, watermarking, rendering, extraction, form filling, encryption, compression, attachments, bookmarks, and metadata management.
      MIT

    Appeared in Searches