Document Processing
Filegraph document-processing is an MCP server that extracts document text, manipulates PDFs, and performs OCR on images for agent-driven workflows.
About
Filegraph document-processing is a hosted MCP server aimed at developers who need reliable text extraction, PDF operations, and OCR without shipping their own conversion microservice first. The registry pins version 1.0.1 with an SSE remote at api.filegraph.ai/mcp, and points to the docconvert project on GitHub for operators who want to trace implementation details. In a solo-developer stack, this typically appears when you ingest user uploads, parse contracts for RAG, split PDFs before summarization, or pull text from scanned receipts in a side project. Your Claude Code or Cursor session calls MCP tools instead of shelling out to ad hoc scripts. It complements storage and vector DB choices but does not replace them. Expect intermediate setup: SSE transport support in the client, Filegraph credentials, and attention to file size and privacy because processing happens on Filegraph infrastructure.
- Remote MCP over SSE at https://api.filegraph.ai/mcp (version 1.0.1)
- Extract text from documents plus manipulate PDFs from agent tools
- OCR on images for scanned uploads and screenshots
- Source repository: github.com/filegraph/docconvert
- Document-processing focused server name in MCP registry
Document Processing by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --transport sse document-processing https://api.filegraph.ai/mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Transport | SSE |
|---|---|
| Auth | None |
What it does
Let your agent extract text from office files, edit PDFs, and run OCR on images inside document automation flows.
Who is it for?
Best when you're wiring ingestion, RAG, or back-office automations and want a remote document API behind MCP.
Skip if: Skip if you require fully on-prem conversion with no third-party document cloud, or simple markdown-only apps with no binary files.
What you get
Document and image inputs become machine-readable text and structured PDF operations callable through MCP during build and integration work.
- Extracted plain text from supported document and image inputs
- PDF manipulation results returned to the agent for downstream steps
- OCR text suitable for summarization, search indexing, or validation
By the numbers
- Server version 1.0.1; remote URL https://api.filegraph.ai/mcp
- Transport type: sse per MCP registry schema
- Repository: github.com/filegraph/docconvert
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.
123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
Document OCR and PDF MCP toolkit, not a note-taking SKILL or a full document management SaaS UI.
FAQ
Who is Filegraph document-processing for?
Developers and integrators adding PDF, document, and image text extraction to MCP-enabled coding agents.
When should I use Filegraph document-processing?
Use it during Build when pipelines need OCR, PDF edits, or reliable text extraction before search, summarization, or storage.
How do I add Filegraph document-processing to my agent?
Register remote MCP https://api.filegraph.ai/mcp (SSE) in your client, authenticate per Filegraph, then invoke document and OCR tools from the agent.