MCP Document Server logo

MCP Document Server

by Omerisra6

A simple server implementing the Model Context Protocol (MCP) for document search and retrieval. It allows for pluggable document services like local storage and Confluence integration.

View on GitHub

Last updated: N/A

What is MCP Document Server?

The MCP Document Server is a server application that uses the Model Context Protocol (MCP) to enable document search and retrieval. It features a pluggable architecture, allowing integration with various document services.

How to use MCP Document Server?

To use the server, first install dependencies using npm install, build the TypeScript code with npm run build, and then start the server using npm run stdio. It is designed to be used with Cursor, where you can use the search tool to find documents and the create_document tool to create new documents.

Key features of MCP Document Server

  • Document storage and retrieval using MCP

  • Semantic search capabilities

  • Compatible with Cursor and other MCP clients

  • Pluggable document service architecture

  • Local document storage with JSON

  • Confluence integration for searching workspace documents

  • Support for HTML

Use cases of MCP Document Server

  • Searching for documents within a local file system

  • Searching for documents within a Confluence workspace

  • Integrating document search into Cursor workflows

  • Creating new documents directly from Cursor

  • Building custom document services for specific data sources

FAQ from MCP Document Server

How do I configure the Confluence service?

Set the CONFLUENCE_BASE_URL, CONFLUENCE_USERNAME, CONFLUENCE_API_TOKEN, and CONFLUENCE_SPACE environment variables.

Where are local documents stored?

Local documents are stored in the data/documents/ directory, and metadata is stored in data/documents.json.

How do I add a new document service?

Implement the DocumentService interface and register your service in src/services/index.ts.

What authentication method is used for Confluence?

The service uses Basic Authentication with your email and API token, encoded in Base64.

What document formats are supported for local storage?

The local storage service supports both Markdown and HTML formats for document content.