196 boosters for "mcp-server" — open source, verified from GitHub, ready to install
Heuristic scoring (no AI key configured).
"description": "Open-source cross-agent memory layer for coding agents across Cursor, Claude Code, Codex, Windsurf, Gemini CLI, Copilot, Kiro, OpenCode, Antigravity, and Trae via MCP.", "sideEffects": false, "memorix": "./dist/cli/index.js"
Official MCP server that integrates Anytype's API with Claude, enabling developers to programmatically interact with Anytype workspaces and data through Claude's context protocol.
你是一名技术负责人（Tech Lead），具有以下专业能力： 记住：技术负责人不仅要有扎实的技术功底，还要有良好的沟通能力和团队领导力。始终以业务价值为导向，在技术实现和业务需求之间找到最佳平衡点。
A shorthand alias for the /thread command in Claude Code, providing quick access to thread management functionality for developers working with the IDE.
"name": "claude-code-organizer", "description": "Organize all your Claude Code memories, skills, MCP servers, and hooks — see what loads globally vs per-project, then move items between scopes", "name": "ithiria894",
An MCP server for conversation history search and retrieval in Claude Code
Opik MCP Server enables developers to integrate automated prompt optimization directly into Claude through the Model Context Protocol. It's valuable for teams building AI applications who want to systematically improve and test their prompts.
17 Google Maps tools for AI agents — geocode, search, directions, weather, air quality, map images via MCP server or standalone CLI
Tableau MCP Server enables AI agents to directly access, visualize, and analyze Tableau data within Claude, helping teams explore business intelligence without switching tools. Developers and data analysts benefit from seamless integration of Tableau dashboards and datasets into AI-powered workflows.
Purpose: Make agents instantly productive. Follow ONLY patterns proven in this repo; don’t invent abstractions. 1. Copy structure from an existing sample; reference . 2. Implement with same pattern (parse settings -> add services -> ).
A fully autonomous AI research agent that ingests sources into Google NotebookLM, runs deep web research, synthesizes knowledge through cited Q&A and 9 downloadable artifact types, creates polished content drafts, and optionally publishes to social platforms.
In Memoria is a persistent intelligence infrastructure MCP server that enables AI agents and developers to build codebase-aware applications with semantic search and pattern learning capabilities. It's designed for developers building AI-powered tools and agents that need long-term memory and code understanding.
Comet MCP Server integrates Perplexity's Comet browser with Claude, enabling agentic web browsing, deep research, and real-time monitoring directly within Claude Code. Developers and researchers benefit from automated, intelligent web interaction capabilities without leaving their AI workflow.
This MCP server enables Claude to read, write, and manage Notion databases and pages directly through the Model Context Protocol. It's ideal for developers and knowledge workers who want to integrate AI-powered automation with their Notion workflows.
An MCP server that integrates Claude with the Hevy fitness tracking app, enabling AI-powered workout analysis, progress tracking, and fitness insights. Ideal for fitness enthusiasts and developers building AI-assisted health applications.
BrowserStack's Official MCP Server enables AI assistants to automate browser testing, accessibility checks, and cross-platform quality assurance directly within Claude. Developers using BrowserStack can leverage AI to orchestrate complex testing workflows without leaving their coding environment.
Agent Operating Guide provides structured instructions for Claude and other AI agents to safely develop and enhance the Raindrop MCP server while maintaining protocol compliance. It benefits developers using AI coding assistants who need consistent, verifiable guidelines for production-ready changes.
"name": "@cyanheads/mcp-ts-core", "version": "0.2.11", "mcpName": "io.github.cyanheads/mcp-ts-core",
"name": "@context-sync/server", "description": "Universal Context layer McP server", "main": "dist/index.js",
The Outline API is not purely RESTful. All endpoints use POST and never GET, PUT, or any other HTTP method.
"name": "matryoshka-rlm", "version": "0.2.17", "description": "Recursive Language Model - Process documents larger than LLM context windows",
