MCP PDF Forms
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP PDF Forms extract form fields from my tax document.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP PDF Forms
A PDF form manipulation toolkit built with MCP and PyMuPDF.
Features
Find PDF files across multiple directories
Extract form field information from PDF files
Visualize form fields in PDF documents
Related MCP server: PDF MCP Server
Installation
# Install package from PyPI
pip install mcp_pdf_forms
# Or install from source
git clone https://github.com/Wildebeest/mcp_pdf_forms.git
cd mcp_pdf_forms
pip install -e .Command Line Tool
After installation, you can use the mcp-pdf-forms command to start the server:
# Start the server with one or more directories to scan for PDFs
mcp-pdf-forms examplesYou can also add it to Claude Code as an MCP:
claude mcp add pdf-forms mcp-pdf-forms .Usage
Once installed, you can use the package to work with PDF forms. The package provides tools through the MCP interface.
PDF Discovery Tool
The PDF Discovery tool helps you find PDF files across specified directories.
Input: Directory paths to search for PDFs
Output: List of PDF files found in the specified directories
Usage: Use this to quickly locate all PDF files in your project or specified folders
Form Field Extraction Tool
The Form Field Extraction tool extracts information about all form fields in a PDF document.
Input: Path to a PDF file
Output: Detailed information about each form field including field name, type, position, and other properties
Usage: Use this to analyze form structure and understand the fields available for filling
Field Highlight Visualization Tool
The Field Highlight tool creates a visual representation of form fields in the PDF.
Input: Path to a PDF file
Output: Modified PDF with all form fields highlighted for easy identification
Usage: Use this to visually inspect the layout and position of form fields in your document
Libraries Used
MCP - Machine Conversation Protocol framework
PyMuPDF - Python bindings for MuPDF, a high-performance PDF library
License
MIT
Available Tools
6 toolsextract_form_fieldsC
Extract all form fields from a PDF
Args:
pdf_path: Path to the PDF file
Returns:
Dictionary of form field names and their properties
Inputs: pdf_path (required).
extract_textA
Extract text from PDF pages
Args:
pdf_path: Path to the PDF file
start_page: Page number to start extraction (0-indexed). If None, starts from first page.
end_page: Page number to end extraction (0-indexed, inclusive). If None, ends at start_page if specified, otherwise extracts all pages.
Returns:
If extracting a single page: string containing the page text
If extracting multiple pages: dictionary mapping page numbers to page text
Inputs: pdf_path (required), start_page, end_page.
highlight_form_fieldA
Generate an image with the specified form field highlighted with a red box
Args:
pdf_path: Path to the PDF file
field_name: Name of the form field to highlight
Returns:
Image of the page with the field highlighted
Inputs: pdf_path (required), field_name (required).
list_pdfsB
List PDF files in configured base paths
Args:
path_filter: Optional string to filter PDF paths
Returns:
List of PDF paths matching the filter
Inputs: path_filter.
render_pdf_pageB
Generate an image of a PDF page without any highlighting
Args:
pdf_path: Path to the PDF file
page_num: Page number to render (0-indexed)
zoom: Zoom factor for rendering (higher values for better quality)
Returns:
Image of the specified page
Inputs: pdf_path (required), page_num, zoom.
search_textA
Search for text pattern in a PDF file
Args:
pdf_path: Path to the PDF file
pattern: Regular expression pattern to search for
case_sensitive: Whether to perform case-sensitive matching
start_page: Page number to start search (0-indexed). If None, starts from first page.
end_page: Page number to end search (0-indexed, inclusive). If None, searches all pages.
Returns:
List of matches with page number, match text, and context
Inputs: pdf_path (required), pattern (required), case_sensitive, start_page, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no ambiguity. extract_form_fields handles form-specific metadata, extract_text retrieves raw text, highlight_form_field visually marks form fields, list_pdfs enumerates files, render_pdf_page generates page images, and search_text performs pattern matching. The descriptions reinforce these unique roles, making tool selection straightforward.
All tools follow a consistent verb_noun pattern with snake_case, such as extract_form_fields, highlight_form_field, and render_pdf_page. The naming is predictable and readable throughout, with no deviations or mixed conventions, enhancing clarity and usability.
With 6 tools, the server is well-scoped for PDF form and content processing. Each tool earns its place by covering distinct aspects like extraction, rendering, listing, and searching, without being overly sparse or bloated. This count aligns well with the domain's typical operations.
The tool set provides strong coverage for PDF form and text operations, including extraction, rendering, listing, and searching. A minor gap exists in form field modification (e.g., fill_form or update_form_field), but agents can work around this by using other tools or external methods. Core workflows are well-supported.
Maintenance
Related MCP Connectors
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
MCP server for the PDFGate API. Generate PDFs, manage documents and handle e-signatures.
MCP server for managing FormDesigner forms, fields, logic rules, themes, and entries
MCP server for Api2Pdf — generate PDFs & images from HTML, URLs or office files; merge, barcodes.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that provides comprehensive PDF processing capabilities including text extraction, image extraction, table detection, annotation extraction, metadata retrieval, page rendering, and document structure analysis.-
- AlicenseNot gradedqualityBmaintenanceAn MCP server for PDF form filling, basic editing, and OCR text extraction. It enables users to merge, rotate, annotate, and sign PDFs, while also supporting text extraction from both searchable and scanned image-based documents.15Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides tools for reading, writing, and manipulating PDF files, including text extraction, metadata retrieval, and merging or splitting documents. It also enables users to create PDFs from plain text and convert specific pages or entire documents into images.39 npm1ISC
- AlicenseAqualityDmaintenanceAn MCP server for local PDF manipulation including merging, splitting, rotating, watermarking, and text extraction. It works with various MCP-compatible clients and processes PDFs entirely on-device without cloud services.1118 npmMIT