Home / MCP registry index / ai.filegraph/document-processing
ai.filegraph/document-processing
ai.filegraph/document-processing in the official MCP registry.
Endpoint https://api.filegraph.ai/mcp. Source: github.com/filegraph/docconvert.
The registry describes it as: Extract text from documents, manipulate PDFs, and perform OCR on images.
We read its 9 tools on 2026-10-21. Nothing in them matched our tool-poisoning rules. It also sets server instructions, text a client puts in front of the model on connect; those were read too.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
filegraph_api_overview filegraph_text_extraction_docs filegraph_pdf_text_conversion_docs filegraph_pdf_manipulation_docs filegraph_pdf_security_docs filegraph_image_processing_docs filegraph_office_documents_docs filegraph_html_processing_docs filegraph_security_docs
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/ai-filegraph-document-processing)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.