Document Processing is a remote MCP server that gives an AI agent 9 tools, among them filegraph_api_overview, filegraph_html_processing_docs, filegraph_image_processing_docs. It answers at https://api.filegraph.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Extract text from documents, manipulate PDFs, and perform OCR via FileGraph API.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
filegraph_api_overview | API overview: authentication, rate limits, errors, and available endpoint groups. |
filegraph_html_processing_docs | Docs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots. Inputs: language, endpoint |
filegraph_image_processing_docs | Docs for /image/to-text, /image/to-pdf, /image/resize — extract text via ocr, convert images to pdf, resize images. Inputs: language, endpoint |
filegraph_office_documents_docs | 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. Inputs: language, endpoint |
filegraph_pdf_manipulation_docs | Docs for /pdf/merge, /pdf/split, /pdf/compress, /pdf/rotate — merge, split, compress, and rotate pdf files. Inputs: language, endpoint |
filegraph_pdf_security_docs | Docs for /pdf/encrypt, /pdf/decrypt — encrypt and decrypt pdf files with password protection. Inputs: language, endpoint |
filegraph_pdf_text_conversion_docs | Docs for /pdf/to-text, /pdf/to-docx, /pdf/to-image — extract text with ocr, convert pdf to docx or images. Inputs: language, endpoint |
filegraph_security_docs | 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. Inputs: language, endpoint |
filegraph_text_extraction_docs | 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. Inputs: language, endpoint |
Every block below points at https://api.filegraph.ai/mcp. Pick your client and copy.
claude mcp add --transport http document-processing https://api.filegraph.ai/mcp
{
"mcpServers": {
"document-processing": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.filegraph.ai/mcp"]
}
}
}{
"mcpServers": {
"document-processing": {
"url": "https://api.filegraph.ai/mcp"
}
}
}{
"servers": {
"document-processing": {
"type": "http",
"url": "https://api.filegraph.ai/mcp"
}
}
}{
"context_servers": {
"document-processing": {
"url": "https://api.filegraph.ai/mcp"
}
}
}{
"mcpServers": {
"document-processing": {
"serverUrl": "https://api.filegraph.ai/mcp"
}
}
}{
"mcpServers": {
"document-processing": {
"url": "https://api.filegraph.ai/mcp"
}
}
}name: document-processing
version: 0.0.1
schema: v1
mcpServers:
- name: document-processing
type: streamable-http
url: https://api.filegraph.ai/mcp{
"mcpServers": {
"document-processing": {
"httpUrl": "https://api.filegraph.ai/mcp"
}
}
}{
"mcpServers": {
"document-processing": {
"type": "http",
"url": "https://api.filegraph.ai/mcp"
}
}
}{
"mcpServers": {
"document-processing": {
"url": "https://api.filegraph.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.filegraph.ai%2Fmcp&type=streamable_http&id=document-processing&name=document-processing
It answered our last check on 17 October 2026 in 645 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by filegraph.ai and served from api.filegraph.ai, the vendor's own domain: https://api.filegraph.ai/mcp.
9, as returned by the server's own tools/list on 7 September 2026: filegraph_api_overview, filegraph_html_processing_docs, filegraph_image_processing_docs, filegraph_office_documents_docs, filegraph_pdf_manipulation_docs, filegraph_pdf_security_docs, filegraph_pdf_text_conversion_docs, filegraph_security_docs, and 1 more.
It answered our last check on 17 October 2026 in 645 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.filegraph.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.filegraph. Endpoint host: api.filegraph.ai. ARD identifier: urn:air:ai.filegraph:mcp:document-processing.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.