Needle MCP Server

Created By
JANHMSa year ago
Integration of Needle in modelcontextprotocol
Overview

what is Needle MCP Server?

Needle MCP Server is an implementation of a Model Context Protocol (MCP) server that integrates AI capabilities, specifically with Claude, to manage and search through document collections utilizing AI-powered Retrieval Augmented Generation (RAG).

how to use Needle MCP Server?

To use the Needle MCP Server, users can integrate the server with their document collections, allowing natural language queries to manage and retrieve documents effectively. Detailed installation instructions can be found in the project's GitHub repository.

key features of Needle MCP Server?

  • Document Collection Management: Users can create and manage collections of documents.
  • File Integration: Add files to collections easily via URLs.
  • Smart Search: Execute semantic search to find relevant documents across collections.
  • RAG Support: Supports advanced Retrieval Augmented Generation functionalities.
  • Intuitive Error Handling: Provides clear feedback to improve user experience.

use cases of Needle MCP Server?

  1. Managing and searching large document repositories in legal or academic settings.
  2. Enhancing research workflows by quickly retrieving relevant information from vast collections.
  3. Assisting content creators with document management and retrieval for writing and editing projects.

FAQ from Needle MCP Server?

  • What is the main function of Needle MCP Server?

It allows users to manage and search document collections using natural language queries with AI integration.

  • Can I add any file type to the document collections?

Yes, users can add files through URLs, provided that the files are supported in the system.

  • Is there documentation available for setup?

Yes, detailed installation and usage documentation can be found on the GitHub repository.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
JANHMS
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago