Skip to main content

PDForm MCP

This is an MCP server intended to enable LLMs to work with PDFs on a deep level. This has a focus on enabling LLMs to understand form-fillable PDFs (hence the name) but is not necessarily limited to that capacity.

Uses PyMuPDF under the hood for all operations.

Current capabilities:

  • List and describe acroform fields
  • Read document metadata
  • Read and write low-level PDF dictionaries
  • Merge PDFs
  • Extract pages from PDFs
  • Read page metadata
  • Screenshot the PDF (for visual inspection by multi-modal models)
  • Understand the layout of the PDF (text, images, drawings, etc...)
  • Extract text from the PDF
  • Locate text (such as input labels) on the page

Installation

Dependencies: pipx

This option runs the MCP server in a virtual environment rather than installing directly to your system Python environment, avoiding potential dependency clashes with other software you may have installed.

claude mcp add pdform-mcp -- pipx run pdform-mcp

or

pipx install pdform-mcp
claude mcp add pdform-mcp -- pdform-mcp

The first option downloads and runs the MCP in an ephemeral virtual environment without installing, the second downloads and installs the tool to a dedicated permanent virtual environment.

Dependencies: Python 3.12+

This method is potentially unsafe, as it installs directly to your system Python environment, but this is less of a problem on Windows as most Windows software does not rely on Python. This method will not at work at all on some Linux distributions which forbid installation of packages to the system Python environment (e.g. Ubuntu).

pip install pdform-mcp
claude mcp add pdform-mcp -- pdform-mcp

Note: If you are on Windows, for this to work you will have to set up your PATH so that pip and any tools it installs are visible to your shell.

Metadata

Release files for pdform-mcp 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pdform-mcp 0.2.0
File Size Uploaded Provenance
pdform_mcp-0.2.0.tar.gz 16.3 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for pdform-mcp 0.2.0
File Interpreter ABI Platform
pdform_mcp-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 40.9 kB

Release files / pdform_mcp-0.2.0.tar.gz

Download URL pdform_mcp-0.2.0.tar.gz
Size 16.3 kB
Tags Source
SHA-256 checksum
How to use checksums
92e104efac689e85c3dc4a9f4d79c284b058223eb25153311e07607aa9af43cf
BLAKE2b-256 checksum
How to use checksums
1d96aadcde8f03b5803beaf58bf5f75965d95e31e621090ae2cd44b306c3ae22
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.1 {"installer":{"name":"uv","version":"0.10.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Red Hat Enterprise Linux","version":"8.10","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / pdform_mcp-0.2.0-py3-none-any.whl

Download URL pdform_mcp-0.2.0-py3-none-any.whl
Size 24.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
50ccef86cefdb255fea33c82b8b7f978ab5ca15124446dc59228c0b9b023513c
BLAKE2b-256 checksum
How to use checksums
9c90bf69ca4701abeb185e31ab617bba4145a75a07dd6c7cf42735029eb16778
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.10.1 {"installer":{"name":"uv","version":"0.10.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Red Hat Enterprise Linux","version":"8.10","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for pdform-mcp 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page