MCP PDF Forms provides local PDF discovery, form-field inspection, page rendering and text extraction through a Python MCP server.
MCP PDF Forms provides local PDF discovery, form-field inspection, page rendering and text extraction through a Python MCP server.
The server uses PyMuPDF to find PDFs, extract form-widget information, highlight a selected field and render pages. It also implements text extraction and pattern search. These tools help an assistant inspect the actual document rather than guess field names from its appearance.
The Python package defines an mcp-pdf-forms console entry point. Its documented launch takes one or more directories to scan. Configure those paths for the documents you intend to inspect, then connect over stdio. The package metadata requires Python 3.11 or later.
Start with a test PDF containing known form widgets. Extract their names and positions, highlight one and inspect the rendered image. A flattened or scanned page may have no interactive form fields even when it visually resembles a form. Text extraction is different from OCR and should be checked against the page when the document contains images or unusual encoding.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| list_pdfs | List PDFs in the configured paths. |
| extract_form_fields | Inspect interactive PDF form widgets. |
| highlight_form_field | Render a PDF with a selected field highlighted. |
| render_pdf_page | Render a selected PDF page. |
| extract_text | Extract text from a PDF or page range. |
| search_text | Find text matches in a PDF. |
{
"mcpServers": {
"pdf-forms": {
"command": "mcp-pdf-forms",
"args": [
"/ABSOLUTE_PATH/test-pdfs"
]
}
}
}Python 3.11 or later, the mcp_pdf_forms package and access to the selected PDF directories.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
Connect the Notion MCP server to search workspace content and work with pages and databases through Notion’s hosted OAuth service.
Search Linear issues and projects, inspect work context and manage updates through Linear’s hosted MCP server with OAuth.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.