
Mcp File Processor
- Updated June 28, 2026
- IntelagentStudios/Intelagent-MCPs
Intelagent MCP File Processor is a MCP server that extracts text, keywords, language, and RAG chunks from files for agent-driven ingestion pipelines.
About
Intelagent MCP File Processor is a stdio Model Context Protocol server that turns raw files into structured inputs for retrieval-augmented generation. developers shipping AI features in Claude Code, Cursor, or Codex can call it from the agent instead of bolting together one-off extractors and chunkers. The server focuses on four complementary steps: text extraction, keyword extraction, language detection, and chunking tuned for RAG workflows. That makes it useful when you are prototyping a knowledge assistant, indexing docs for support bots, or preparing customer uploads before they hit your vector database. Version 0.1.1 ships on npm as @intelagent/mcp-file-processor with the standard MCP server schema. It is an integration layer, not a hosted search product—you still choose embeddings, storage, and orchestration elsewhere in your stack.
- Extracts plain text from uploaded or referenced files for downstream indexing
- Runs keyword extraction to surface salient terms before embedding
- Detects document language to route parsers and metadata correctly
- Splits content into RAG-ready chunks suitable for vector ingestion
- Stdio MCP package via npx @intelagent/mcp-file-processor (v0.1.1)
Mcp File Processor by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add mcp-file-processor -- npx -y @intelagent/mcp-file-processorAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @intelagent/mcp-file-processor |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | June 28, 2026 |
| Repository | IntelagentStudios/Intelagent-MCPs ↗ |
What it does
Ingest local documents into RAG pipelines by extracting text, keywords, language, and chunks from files inside the agent.
Who is it for?
Best when you're wiring document upload or repo docs into a vector store from Claude Code, Cursor, or Codex during Build.
Skip if: Skip if you only need full managed ingestion with OCR, layout models, and hosted search in one SaaS bundle.
What you get
Your assistant can normalize documents through one MCP tool surface so you spend time on retrieval quality and product UX instead of preprocessing glue code.
- Extracted text and metadata-ready chunks from agent-requested files
- Keywords and detected language to tag chunks before embedding
- Repeatable MCP tool calls instead of one-off preprocessing scripts
By the numbers
- Server version 0.1.1 on npm as @intelagent/mcp-file-processor
- Stdio transport via npx runtimeHint
- Four documented capabilities: text extraction, keywords, language detection, chunking
README.md
Intelagent MCPs
Open-source Model Context Protocol servers by Intelagent. Each server is a standalone npm package usable with Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.
Servers
| Package | Description | Status |
|---|---|---|
@intelagent/mcp-enrichment |
Company, contact, email & phone enrichment via Clearbit, Hunter.io, Twilio | Available |
@intelagent/mcp-file-processor |
Document text extraction, keyword detection, chunking | Available |
@intelagent/mcp-web-research |
Web search, page fetch, research synthesis | Planned |
@intelagent/mcp-approval-queue |
Human-in-the-loop approval workflows | Planned |
@intelagent/mcp-knowledge-grid |
Document indexing, semantic search, context composition | Planned |
Quick Start
# Clone and install
git clone https://github.com/IntelagentStudios/Intelagent-MCPs.git
cd Intelagent-MCPs
npm install
npm run build
# Run the enrichment server (mock mode — no API keys needed)
node packages/enrichment/dist/index.js
Add to Claude Code
Create or edit .mcp.json in your project root:
{
"mcpServers": {
"enrichment": {
"command": "node",
"args": ["/path/to/Intelagent-MCPs/packages/enrichment/dist/index.js"],
"env": {
"CLEARBIT_API_KEY": "sk-...",
"HUNTER_API_KEY": "...",
"TWILIO_ACCOUNT_SID": "...",
"TWILIO_AUTH_TOKEN": "..."
}
}
}
}
All servers work in mock mode when API keys are omitted — great for development and testing.
Development
npm install # Install all dependencies
npm run build # Build all packages
npm test # Run all tests
Adding a New Server
- Create
packages/<server-name>/withpackage.json,tsconfig.json, andsrc/ - Use
@intelagent/mcp-sharedfor the server bootstrap (createMCPServer) - Define tools in
tools.ts, wire up inindex.ts - Add tests in
__tests__/
See packages/enrichment as a reference implementation.
Shared Utilities
@intelagent/mcp-shared provides:
createMCPServer()— Reusable MCP server bootstrap with tool/resource registration and stdio transport- Validation helpers — Email, domain, phone format validation
License
MIT
Recommended MCP Servers
How it compares
MCP file-preprocessing integration, not a hosted vector database or embedding API.
FAQ
Who is Intelagent MCP File Processor for?
and developers adding RAG or doc Q&A to agents who want extraction, keywords, language detection, and chunking exposed as MCP tools.
When should I use Intelagent MCP File Processor?
Use it in the Build phase while you prototype ingestion—before you commit to a fixed chunking strategy or production embedding pipeline.
How do I add Intelagent MCP File Processor to my agent?
Register the stdio server in your MCP config with runtime npx and package @intelagent/mcp-file-processor, then invoke its tools from Claude Code, Cursor, or another MCP-capable client.