Document Processing

filegraph/docconvert

This connects Claude to Filegraph's document processing pipeline over SSE. You get text extraction from common document formats, PDF manipulation tools, and OCR for images containing text. Reach for this when you need Claude to parse invoices, contracts, or scanned documents without bouncing through manual copy-paste or building your own OCR workflow. The remote API means no local dependencies to manage, though you'll need network access. Useful for automating document intake workflows or building assistants that need to read from uploaded files in various formats.

tools: 9
transport: SSE
last updated: Jan 24, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://api.filegraph.ai/mcp --name document-processing --transport sse

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport sse document-processing https://api.filegraph.ai/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 9 tools

Verified live against the running server on Nov 6, 2026.

filegraph_api_overviewAPI overview: authentication, rate limits, errors, and available endpoint groups.

API overview: authentication, rate limits, errors, and available endpoint groups.

No parameters. Call it with no arguments.

filegraph_text_extraction_docsDocs for /any/to-text, /any/info, /any/to-struct — extract text with smart format detection and ocr, analyze file metadata, extract structured data with LLM.2 params

Docs for /any/to-text, /any/info, /any/to-struct — extract text with smart format detection and ocr, analyze file metadata, extract structured data with LLM.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /any/to-text, /any/info, /any/to-struct

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_pdf_text_conversion_docsDocs for /pdf/to-text, /pdf/to-docx, /pdf/to-image — extract text with ocr, convert pdf to docx or images.2 params

Docs for /pdf/to-text, /pdf/to-docx, /pdf/to-image — extract text with ocr, convert pdf to docx or images.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /pdf/to-text, /pdf/to-docx, /pdf/to-image

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_pdf_manipulation_docsDocs for /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate — merge, split, compress, and rotate pdf files.2 params

Docs for /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate — merge, split, compress, and rotate pdf files.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_pdf_security_docsDocs for /pdf/encrypt, /pdf/decrypt — encrypt and decrypt pdf files with password protection.2 params

Docs for /pdf/encrypt, /pdf/decrypt — encrypt and decrypt pdf files with password protection.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /pdf/encrypt, /pdf/decrypt

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_image_processing_docsDocs for /image/to-text, /image/to-pdf, /image/resize — extract text via ocr, convert images to pdf, resize images.2 params

Docs for /image/to-text, /image/to-pdf, /image/resize — extract text via ocr, convert images to pdf, resize images.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /image/to-text, /image/to-pdf, /image/resize

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_office_documents_docsDocs for /docx/to-text, /docx/to-pdf, /xlsx/to-text, /xlsx/to-pdf, /xlsx/to-csv, /pptx/to-text, /pptx/to-pdf, /pptx/to-images — extract text/data, convert word/excel/powerpoint to pdf/csv/images.2 params

Docs for /docx/to-text, /docx/to-pdf, /xlsx/to-text, /xlsx/to-pdf, /xlsx/to-csv, /pptx/to-text, /pptx/to-pdf, /pptx/to-images — extract text/data, convert word/excel/powerpoint to pdf/csv/images.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /docx/to-text, /docx/to-pdf, /xlsx/to-text, /xlsx/to-pdf, /xlsx/to-csv, /pptx/to-text, /pptx/to-pdf, /pptx/to-images

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_html_processing_docsDocs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots.2 params

Docs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /html/to-text, /html/to-pdf, /html/to-image

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.

filegraph_security_docsDocs for /security/pdf/redact, /security/text/redact, /security/pdf/lock, /security/pdf/unlock, /security/detect-tracking — redact sensitive pdf content, redact PII from extracted text, lock/unlock pdfs, detect/remove tracking pixels.2 params

Docs for /security/pdf/redact, /security/text/redact, /security/pdf/lock, /security/pdf/unlock, /security/detect-tracking — redact sensitive pdf content, redact PII from extracted text, lock/unlock pdfs, detect/remove tracking pixels.

Parameters* required

endpointvalue

Get docs for a single endpoint only (reduces response size). Valid values: /security/pdf/redact, /security/text/redact, /security/pdf/lock, /security/pdf/unlock, /security/detect-tracking

languagevalue

Language for code examples (e.g. 'go_native', 'shell_curl'). Defaults to Python HTTPX.