Needle MCP Server
OfficialThe Needle MCP Server enables efficient document organization, retrieval, and semantic search using Claude's large language model and the Needle ecosystem.
Document Management: Add, organize, and retrieve documents efficiently
Collection Operations: Create, list, and manage document collections with detailed metadata and statistics
File Operations: Add files via URLs and monitor processing status
Semantic Search: Perform advanced natural language searches to find conceptually related content within document collections
Integration: Seamlessly integrate with Claude Desktop and Needle for enhanced document handling
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Needle MCP Server search for quarterly sales projections in the finance documents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Build Agents with Needle MCP Server
MCP (Model Context Protocol) server to manage documents and perform searches using Needle through Claude's Desktop Application.
Table of Contents
Related MCP server: Documentation MCP Server
Overview
Needle MCP Server allows you to:
Organize and store documents for quick retrieval.
Perform powerful searches via Claude's large language model.
Integrate seamlessly with the Needle ecosystem for advanced document management.
MCP (Model Context Protocol) standardizes the way LLMs connect to external data sources. You can use Needle MCP Server to easily enable semantic search tools in your AI applications, making data buried in PDFs, DOCX, XLSX, and other files instantly accessible by LLMs.
We recommend using our remote MCP server for the best experience - no local setup required.
Features
Document Management: Easily add and organize documents on the server.
Search & Retrieval: Claude-based natural language search for quick answers.
Easy Integration: Works with Claude Desktop and Needle collections.
Usage
Commands in Claude Desktop
Below is an example of how the commands can be used in Claude Desktop to interact with the server:
Open Claude Desktop and connect to the Needle MCP Server.
Use simple text commands to search, retrieve, or modify documents.
Review search results returned by Claude in a user-friendly interface.
Result in Needle
https://github.com/user-attachments/assets/0235e893-af96-4920-8364-1e86f73b3e6c
Youtube Video Explanation
For a full walkthrough on using the Needle MCP Server with Claude and Claude Desktop, watch this YouTube explanation video.
Installation
1. Remote MCP Server (Recommended)
Claude Desktop Config
Create or update your config file:
For MacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonFor Windows:
%APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"needle": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.needle.app/mcp",
"--header",
"Authorization:Bearer ${NEEDLE_API_KEY}"
],
"env": {
"NEEDLE_API_KEY": "<your-needle-api-key>"
}
}
}
}Cursor Config
Create or update .cursor/mcp.json:
{
"mcpServers": {
"needle": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.needle.app/mcp",
"--header",
"Authorization:${NEEDLE_AUTH_HEADER}"
],
"env": {
"NEEDLE_AUTH_HEADER": "Bearer <your-needle-api-key>"
}
}
}
}Get your API key from Needle Settings.
We provide two endpoints:
Streamable HTTP:
https://mcp.needle.app/mcp(recommended)SSE:
https://mcp.needle.app/sse
Note: MCP deprecated SSE endpoints in the latest specification, so newer clients should prefer the Streamable HTTP endpoint.
2. Local Installation
Clone the repository:
git clone https://github.com/needle-ai/needle-mcp.gitInstall UV globally using Homebrew:
brew install uvCreate your config file:
For MacOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonFor Windows:
%APPDATA%/Claude/claude_desktop_config.json
Claude Desktop Config
{
"mcpServers": {
"needle": {
"command": "uv",
"args": ["--directory", "/path/to/needle-mcp", "run", "needle-mcp"],
"env": {
"NEEDLE_API_KEY": "<your-needle-api-key>"
}
}
}
}Cursor Config
{
"mcpServers": {
"needle": {
"command": "uv",
"args": ["--directory", "/path/to/needle-mcp", "run", "needle-mcp"],
"env": {
"NEEDLE_API_KEY": "<your-needle-api-key>"
}
}
}
}Replace
/path/to/needle-mcpwith your actual repository pathAdd your Needle API key
Restart Claude Desktop
Installing via Smithery
npx -y @smithery/cli install needle-mcp --client claude3. Docker Installation
Clone and build:
git clone https://github.com/needle-ai/needle-mcp.git
cd needle-mcp
docker build -t needle-mcp .Add to your Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"needle": {
"command": "docker",
"args": ["run", "--rm", "-i", "needle-mcp"],
"env": {
"NEEDLE_API_KEY": "<your-needle-api-key>"
}
}
}
}Restart Claude Desktop
Usage Examples
"Create a new collection called 'Technical Docs'"
"Add this document to the collection, which is https://needle.app"
"Search the collection for information about AI"
"List all my collections"
Troubleshooting
If not working:
Make sure
uvis installed globally (if not, uninstall withpip uninstall uvand reinstall withbrew install uv)Or find
uvpath withwhich uvand replace"command": "uv"with the full pathVerify your Needle API key is correct
Check if the needle-mcp path in config matches your actual repository location
Reset Claude Desktop Configuration
If you're seeing old configurations or the integration isn't working:
Find all Claude Desktop config files:
find / -name "claude_desktop_config.json" 2>/dev/nullRemove all Claude Desktop data:
On MacOS:
rm -rf ~/Library/Application\ Support/Claude/*On Windows: Delete contents of
%APPDATA%/Claude/
Create a fresh config with only Needle:
mkdir -p ~/Library/Application\ Support/Claude
cat > ~/Library/Application\ Support/Claude/claude_desktop_config.json
<< 'EOL'
{
"mcpServers": {
"needle": {
"command": "uv",
"args": [
"--directory",
"/path/to/needle-mcp",
"run",
"needle-mcp"
],
"env": {
"NEEDLE_API_KEY": "your_needle_api_key"
}
}
}
}
EOLCompletely quit Claude Desktop (Command+Q on Mac) and relaunch it
If you still see old configurations:
Check for additional config files in other locations
Try clearing browser cache if using web version
Verify the config file is being read from the correct location
Available Tools
7 toolsneedle_add_fileAInspect
Add a new document to a Needle collection by providing a URL for download. Supports multiple file formats including: - PDF documents - Microsoft Word files (DOC, DOCX) - Plain text files (TXT) - Web pages (HTML)
The document will be:
1. Downloaded from the provided URL
2. Processed for text extraction
3. Indexed for semantic search
Use this tool when you need to:
- Add new documents to a collection
- Make documents searchable
- Expand your knowledge base
Important: Documents require processing time before they're searchable.
Check processing status using needle_list_files before searching new content.Inputs: collection_id (required), name (required), url (required).
needle_create_collectionAInspect
Create a new document collection in Needle for organizing and searching documents. A collection acts as a container for related documents and enables semantic search across its contents. Use this tool when you need to: - Start a new document organization - Group related documents together - Set up a searchable document repository Returns a collection ID that's required for subsequent operations. Choose a descriptive name that reflects the collection's purpose for better organization.
Inputs: name (required).
needle_get_collection_detailsAInspect
Fetch comprehensive metadata about a specific Needle collection. Provides detailed information about the collection's configuration, creation date, and current status. Use this tool when you need to: - Verify a collection's existence and configuration - Check collection metadata before operations - Get creation date and other attributes Requires a valid collection ID and returns detailed collection metadata. Will error if collection doesn't exist.
Inputs: collection_id (required).
needle_get_collection_statsAInspect
Retrieve detailed statistical information about a Needle collection's contents and status. Provides metrics including: - Total number of documents - Processing status of documents - Storage usage and limits - Index status and health Use this tool to: - Monitor collection size and growth - Verify processing completion - Check collection health before operations Essential for ensuring collection readiness before performing searches.
Inputs: collection_id (required).
needle_list_collectionsAInspect
List Needle collections. Returns maximum of 20 results. Get more results by increasing the offset. Returns detailed information including collection IDs, names, and creation dates. Use this tool when you need to: - Get an overview of available document collections - Find collection IDs for subsequent operations - Verify collection existence before performing operations The response includes metadata that's required for other Needle operations.
Inputs: offset.
needle_list_filesAInspect
List all documents stored within a specific Needle collection with their current status. Returns detailed information about each file including: - File ID and name - Processing status (pending, processing, complete, error) - Upload date and metadata Use this tool when you need to: - Inventory available documents - Check processing status of uploads - Get file IDs for reference - Verify document availability before searching Essential for monitoring document processing completion before performing searches.
Inputs: collection_id (required).
needle_searchAInspect
Perform intelligent semantic search across documents in a Needle collection. This tool uses advanced embedding technology to find relevant content based on meaning, not just keywords. The search: - Understands natural language queries - Finds conceptually related content - Returns relevant text passages with source information - Ranks results by semantic relevance
Use this tool when you need to:
- Find specific information within documents
- Answer questions from document content
- Research topics across multiple documents
- Locate relevant passages and their sources
More effective than traditional keyword search for:
- Natural language questions
- Conceptual queries
- Finding related content
Returns matching text passages with their source file IDs.Inputs: collection_id (required), query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap: collection management (create, list, get details, get stats), file management (add, list), and search. The descriptions explicitly differentiate their functions, such as needle_get_collection_details for metadata vs. needle_get_collection_stats for metrics, eliminating any ambiguity.
All tools follow a consistent verb_noun pattern with the 'needle_' prefix, using snake_case throughout (e.g., needle_create_collection, needle_list_files). This predictable naming scheme makes it easy for agents to understand and select tools based on their actions and targets.
With 7 tools, the server is well-scoped for document management and search, covering essential operations like collection CRUD, file addition, status monitoring, and semantic search. Each tool serves a clear purpose without redundancy, fitting the domain's needs efficiently.
The toolset provides strong coverage for core document management workflows, including collection lifecycle, file processing, and search. A minor gap exists in file deletion or update capabilities, which could limit full CRUD operations, but agents can still perform key tasks like adding, listing, and searching documents effectively.
Maintenance
Related MCP Connectors
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
Ingest, manage, and retrieve documents for RAG-powered AI applications
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Pageform is an AI-native data room platform with a remote MCP server for Claude and other MCP-compatible clients. Upload and organize documents, generate structured data rooms with AI, audit missing materials, create secure share links, and analyze investor engagement directly from your AI assistant. Built for fundraising, investor relations, diligence, and deal workflows. Connect securely through Pageform OAuth. Website: https://pageform.io Documentation: https://pageform.io/docs/integrations/claude
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceA server that connects Claude to your documentation via Inkeep's API, enabling AI-powered interactions with your documentation content.25MIT- FlicenseAqualityDmaintenanceA server that enables Claude to search and access documentation from popular libraries like LangChain, LlamaIndex, and OpenAI directly within conversations.13-
- FlicenseNot gradedqualityDmaintenanceA local document intelligence and knowledge management server for Claude Desktop that provides RAG-powered Q\&A, media transcription, and URL crawling. It features 11 tools for processing various file types and managing a persistent local vector store with zero infrastructure costs.1-
- FlicenseNot gradedqualityDmaintenanceMCP server enabling Claude Desktop to answer questions from local Word and PDF documents by searching a vector index built from their contents.-