MCP Servers

The firewall for AI agents. Open-source policy enforcement for MCP. Website: policylayer.com Intercept is a deterministic enforcement proxy for the Model Context Protocol (MCP). It sits between an AI agent and an MCP server, evaluating every tools/call request against YAML-defined policies. Violating calls are blocked at the transport layer before reaching the upstream server. MCP gives AI agents

RevolutionAI is an MCP-native freelance marketplace built for SaaS founders who live in their AI tools. Building a startup means constantly context-switching: - Need a dev? → Open Upwork, post job, wait days - Need a designer? → Jump to Dribbble or Fiverr - Need a marketer? → LinkedIn, emails, calls Every switch kills your flow. You're supposed to be building, not bouncing between 10 tabs. Stay in

An MCP server focused only on Overleaf projects (via Overleaf Git sync). .env example: - OVERLEAFTOKEN is required. - projectid can be passed per tool call, or use default PROJECTID. - Overleaf Git access requires a plan that supports Git integration. Add to ~/.config/Claude/claudedesktopconfig.json: - Python 3.13+ - uv package manager MIT - See LICENSE

The open-source alternative to Google's Code Wiki — with MCP. Index any codebase with tree-sitter, generate docs with your LLM, serve them through a full-featured docs site, and expose everything as tools for coding agents via MCP. Like Notion for code agents. Index a project and generate documentation. Defaults to the current directory. Start the docs server. Manage API keys and provider settings

A PTY-based MCP server with strong Windows support, giving MCP-capable AI clients and their agents persistent, interactive shell access via pseudo-terminals (node-pty). Unlike simple exec-based approaches, this keeps PTY-backed shell sessions alive across steps, with bidirectional communication for interactive CLI tools, incremental reads, and session state that carries forward. See the Changelog

An MCP server that brings your curated Obris knowledge into any AI conversation. Use the Chrome extension or upload directly to save knowledge to dedicated topics so you never start another AI chat from zero again. - List topics — Browse all your Obris topics to find the one you need - Pull in knowledge — Retrieve saved bookmarks, highlights, and notes as context for any conversation - Save knowle

A database-backed kanban board that AI coding agents use via MCP (Model Context Protocol). Track issues, features, todos, epics, and diary entries across all your projects — with a web UI for humans and 40+ tools for agents. More screenshots - Persistent project tracking — issues, features, todos, epics, diary entries stored in MySQL/MariaDB - Status workflows — each item type has its own progress

MCP Assistant Web-based MCP client for remote servers and AI tool workflows. MCP Assistant addresses common pain points when working with the Model Context Protocol: - Connect to remote MCP servers from one interface - Manage multiple MCP servers from a single interface - Handle OAuth 2.0 and OpenID Connect flows without manual token juggling - Explore available tools and run them directly from th

A Model Context Protocol (MCP) server for LinkedIn. Search people, companies, and jobs, scrape profiles, and retrieve structured JSON data from any MCP-compatible AI client. Built with FastMCP, Patchright, and a clean hexagonal architecture. The getpersonprofile tool supports granular section scraping. Request only the sections you need: - Main profile (always included) — name, headline, location,

You've had thousands of AI conversations. You can't search any of them. ⬆️ Auto-playing preview — click here for full video with audio Documentation · Quickstart · ❓ FAQ · All 25 Tools If this is useful, a ⭐ helps others find it. Restart Claude. 25 tools available. Keyword search works immediately. Alternative: pip install Setup for specific clients After setup, just say "use brain" in an

English | 日本語 mcp-alphabanana is a Model Context Protocol (MCP) server for generating image assets with Google Gemini. It is built for MCP-compatible clients and agent workflows that need fast image generation, transparent outputs, reference-image guidance, and flexible delivery formats. Keywords: MCP server, Model Context Protocol, Gemini AI, image generation, FastMCP Key capabilities: - Ultra-fa

An Android application that runs as an MCP (Model Context Protocol) server, enabling AI models to fully control an Android device remotely using accessibility services and screenshot capture. The app runs directly on your Android device (or emulator) and exposes an HTTP server (with optional HTTPS) implementing the MCP protocol. AI models like Claude can connect to it and interact with any app on

Search your past ChatGPT conversations directly from Claude Desktop. Switched from ChatGPT to Claude? Now you can ask Claude things like "What did I discuss about marketing strategy in ChatGPT?" and get real answers — without going back to ChatGPT. Step 1 — Export your ChatGPT data In ChatGPT: Settings → Data Controls → Export Data. You'll get an email with a .zip file. Step 2 — Run the installer

stats-compass-mcp Turn your LLM into a data analyst. Multiple data science tools via MCP. Restart your client and start asking questions about your data. Run stats-compass-mcp list-tools to see all available tools. Start your message with "Use stats compass to..." — this tells the AI to use the Stats Compass tools instead of trying to write code or use other methods. Local mode: Start with "Use st

A Model Context Protocol (MCP) server for the Mailchimp Marketing API. 53 tools to query and manage your Mailchimp account directly from Claude. Uses the Mailchimp Marketing API via requests. Not based on the official mailchimp-marketing-python client. I hit too many issues with it so I went with raw HTTP calls instead. - Campaigns - List, search, and inspect campaign details - Reports - Open/clic

Spatio-Temporal Transfer Protocol (STTP) is a typed intermediate representation that encodes conversational state into a compressed, confidence-weighted structure any model can reconstruct. This is the MCP server that exposes that capability as tools. Licensed under Apache-2.0. See LICENSE. Every AI conversation dies when the session ends. The context, the reasoning state, the accumulated understa

Manage MCP servers across 13 AI clients from one CLI. Define a server once. Enable it where you want. Keep unmanaged client entries intact. MCP servers are useful, but managing them across multiple AI clients is repetitive and error-prone: - different config locations - different formats (JSON, JSONC, TOML) - repeated env/header setup - easy to overwrite manual client entries - hard to roll back a

AI can build products. But it still doesn't talk to users. Usercall MCP lets AI agents run user interviews via voice calls and return structured insights with themes and verbatim quotes. Works with Claude Desktop, Cursor, and any MCP-compatible client. AI agents can now build and ship products extremely quickly. But most agents still rely on synthetic feedback or assumptions about users. Usercall

A collection of Model Context Protocol (MCP) servers that provide AI assistants with access to native Apple applications on macOS. - macOS (uses AppleScript and macOS-specific APIs) - Node.js 18+ (22+ for Apple Messages) - Full Disk Access granted to your terminal app (System Settings > Privacy & Security > Full Disk Access) — required for reading the Messages database - The associated Apple app m

Stop fumbling with GUI apps to debug Bluetooth Low Energy devices. blew gives you full BLE control from the macOS command line: scan the airwaves, drill into any device's GATT tree, read and write characteristics, stream live notifications, and even spin up a virtual peripheral that other devices can connect to. - One tool, zero ceremony. Scan, connect, inspect, read, write, subscribe -- each is a

knowledge-to-action-mcp is an MCP server for people whose real project context lives in notes, decisions, roadmaps, and meeting docs, not just code. Most Obsidian MCP servers stop at "read a note" or "search a vault." This one goes further: That means an MCP client can move from: If you work out of Obsidian, your important context is usually spread across: - roadmap notes - meeting notes - decisio

- About the pgEdge Postgres MCP Server - pgEdge Postgres MCP Server - Choosing the Right Solution - Best Practices - Querying the Server - Installing the MCP Server - Quick Start - Quickstart Demo with Northwind - Deploying on Docker - Deploying from Source - Testing the MCP Server Deployment - Configuring the MCP Server - Specifying Configuration Preferences - Using Environment Variables to Speci

A Go MCP server for D&D campaign state management, dice rolling, and session memory. - Serves a Model Context Protocol (MCP) toolset over stdio or streamable HTTP. - Stores campaign data in per-campaign SQLite databases. - Tracks characters, plot events/hooks, world flags, roll history, checkpoints, and session summaries. - Generates session briefs and markdown recaps for fast DM context restorati

Instead of manually checking the Rybbit dashboard, let your AI assistant query analytics data directly: - "How many users visited the site today?" - "Show me the top pages by bounce rate this week" - "What errors occurred in the last hour?" - "Show user journey from homepage to checkout" - "Compare browser usage between mobile and desktop" Or clone and build: Add to your ~/.claude/settings.json or