Back to MCP Catalog

Needle Document Management MCP Server

Knowledge & MemoryPython
Manage and search documents using Needle's document management system
Available Tools

create_collection

Create a new document collection in Needle

list_collections

List all available document collections

add_document

Add a document to a collection by URL or text content

search_collection

Search within a collection using natural language queries

delete_collection

Delete an existing collection

Needle Document Management provides a powerful interface for organizing, storing, and retrieving documents through Claude's Desktop Application. It seamlessly integrates with the Needle ecosystem, allowing users to create collections, add documents, and perform natural language searches powered by Claude's large language model capabilities. This MCP server bridges the gap between Claude's conversational interface and Needle's document management system, enabling users to interact with their document collections through simple text commands. The integration provides an intuitive way to manage knowledge bases and quickly retrieve relevant information from your documents.

Getting Started with Needle Document Management

Needle Document Management allows you to organize documents in collections and perform powerful searches using Claude's natural language capabilities. This integration connects Claude Desktop with Needle's document management system.

Installation Options

Option 1: Install via Smithery (Recommended)

The easiest way to install Needle Document Management is through Smithery:

npx -y @smithery/cli install needle-mcp --client claude

This command automatically configures everything for you.

Option 2: Manual Installation

  1. Clone the repository:
git clone https://github.com/needle-ai/needle-mcp.git
  1. Install UV globally using Homebrew (macOS):
brew install uv
  1. Create a configuration file:

    • For macOS: Create claude_desktop_config.json in ~/Library/Application Support/Claude/
    • For Windows: Create claude_desktop_config.json in %APPDATA%/Claude/
  2. Add the following configuration (replace paths and API key with your own):

{
  "mcpServers": {
    "needle_mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/needle-mcp",
        "run",
        "needle-mcp"
      ],
      "env": {
        "NEEDLE_API_KEY": "your_needle_api_key"
      }
    }
  }
}
  1. Get your Needle API key from needle.xyz
  2. Restart Claude Desktop completely

Using Needle Document Management

Once installed, you can use natural language commands in Claude Desktop to manage your documents:

Collection Management

  • Create a new collection: Create a new collection called "Technical Docs"
  • List all collections: List all my collections
  • Delete a collection: Delete the collection "Old Reports"

Document Management

  • Add documents: Add this document to the collection: https://needle-ai.com
  • Add text: Add this text to my collection: [paste text here]
  • Remove documents: Remove the document about AI basics from my collection

Searching

  • Basic search: Search my collection for information about AI models
  • Advanced search: Find documents in "Technical Docs" that mention neural networks and provide a summary

Tips for Effective Use

  1. Organize by Topic: Create separate collections for different subjects or projects
  2. Use Descriptive Names: Give your collections clear names that reflect their content
  3. Leverage Claude's Understanding: You can ask natural language questions about your documents
  4. Combine with Other Tasks: Ask Claude to analyze search results or create summaries

Troubleshooting

If you encounter issues:

  1. Verify your Needle API key is correct
  2. Ensure Claude Desktop is properly configured
  3. Check that the path to the needle-mcp directory is correct
  4. Restart Claude Desktop after making configuration changes

For more detailed instructions, visit the GitHub repository or watch the YouTube explanation video.

Related MCPs

Knowledge Graph Memory
Knowledge & MemoryTypeScript

A persistent memory system using a local knowledge graph

MemoryMesh
Knowledge & MemoryTypeScript

A knowledge graph server for structured memory persistence in AI models

Cognee
Knowledge & MemoryPython

Knowledge management and retrieval system with code graph capabilities

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.