mcp
the context layer for large codebases.
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
Let your agents instantly understand the world's code. Let Your Agents Instantly Understand Any Git Repo.
Stop integrating code based on hallucinations or poor documentation. Give your agents direct understanding of any GitHub repo to get it right on the first try.
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
open-browser-use is a browser automation layer that stays neutral across agent runtimes. It is also an open-source alternative to the Chrome Browser Use capability recently shipped in Codex.app. For the story behind it, see the Browser Use Deep Dive.
Related contents:
open-computer-use is an open-source Computer Use service wrapped as MCP. Any AI agent or MCP client can use it to run Computer Use on macOS, Linux, and Windows.
Related contents:
Advanced AI-powered penetration testing MCP framework with 150+ security tools and 12+ autonomous AI agents.
HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.
Related contents:
AI-Powered Codebase Analysis.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs.
Code-Graph-RAG parses a multi-language codebase with Tree-sitter, builds a knowledge graph of its structure in Memgraph, and lets you query, edit, and optimise that code in plain English. It works across a monorepo of mixed languages under one unified graph schema.
A portable package format for reusable components that extend AI agents.
Agent Plugins is an open, vendor-neutral standard for packaging reusable components into portable plugins. Its version 1.0.0 specification defines a shared format for Agent Skills and MCP servers that compatible clients can discover and load consistently.
Related contents:
MCP, made portable.
mcporter is a TypeScript runtime, CLI, and code-generation toolkit for the Model Context Protocol — built so AI agents and developers can call any MCP server without boilerplate.
Local-first documentation for AI agents. Up-to-date docs for AI agents — local, instant, plug and play.
Context is an MCP server backed by a community-driven package registry with 100+ popular libraries already built and ready to use. When your AI agent needs documentation, it searches the registry, downloads the right package, and queries it locally — all automatically.
Related contents:
PostgreSQL MCP Server for Schema Intelligence. The Offline-First PostgreSQL MCP That Won't Ruin Your Production.
Capture your schema and statistics into a portable snapshot. Lint it, diff it, validate queries against it, and hand it to your AI assistant. No production credentials on developer machines.
The Open Standard for AI Agent Configuration.
An open directory convention for AI agent configuration. One place for MCP tools, AGENTS.md instructions, Skills, Sub-Agents, Tasks, Memories, and model config — in plain, version-controllable files.
Adds a /-/mcp MCP server to any Datasette instance.
Related contents:
CLI tool for exploring an MCP server.
Related contents:
Ecosystem, Frameworks, Workflows for AI coding agents.
Gentle-AI is NOT an AI agent installer. Most agents are easy to install. It is an ecosystem configurator that equips the AI coding agent(s) you already use with persistent memory, Spec-Driven Development (SDD), curated skills, MCP servers, model routing, a teaching-oriented persona, and bounded native review.
Before: "I installed Claude Code / OpenCode / Cursor, but it's just a chatbot that writes code."
After: Your agent now has memory, skills, workflow, MCP tools, and a persona that actually teaches you.
Related contents:
Tools for Agents
One MCP endpoint, 67 real tools — news, web search, mail, markets, weather, video, storage. Connect an agent once and it has all of them, instead of wiring up a server for each.
Mu is an MCP server and web app for agents and humans. It provides access to the real world through MCP for the agents and let's humans browse or interact with same content in a web app. Access news, web search, mail, markets, weather, video, places, images, files, calendar, contacts and more.
A hook that registers a WebMCP tool with the browser and ties its lifecycle to a React component.
WebMCP lets a page expose JavaScript functions as "tools" that an AI agent (browser-built-in, iframe-hosted, or extension) can discover and call. The site author can expose functionality, and the agent uses this instead of scraping the DOM, a11y tree, or using screenshots.
AI Code Retrieval with 95% Token Reduction.
Model-agnostic MCP server indexes your repo and hands any AI agent — Claude, GPT, Gemini — the exact function, class, or constant. No more 200K-token file dumps. More wins, fewer timeouts, lower bill.
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Related contents:
MCP Server for kubernetes management commands.
MCP Server that can connect to a Kubernetes cluster and manage it. Supports loading kubeconfig from multiple sources in priority order.
Related contents:
A Visualization Language for the AI Era.
Flint is a visualization intermediate language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs. Instead of requiring verbose low-level parameters such as scales, axes, spacing, and layout, the Flint compiler derives optimized chart settings from the data, semantic types, chart type, and encodings. Flint supports 46 chart types, and it supports rendering in Vega-Lite, ECharts, and Chart.js.
Local code intelligence for MCP.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
Network Observability for the AI Era.
eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
The web, wired into your local agent.
wigolo is a local-first server that hands any AI agent the whole web — search, fetch, crawl, extract, cache, and research. In your editor over MCP, in your framework through an SDK, or in your self-hosted stack over REST. No API keys. No cloud. No metered bill.
Because your AI shouldn't hallucinate package names.
Real, up-to-the-second information about NixOS packages, options, Home Manager, nix-darwin, flakes, and friends — served over the Model Context Protocol.
Related contents:
The Application Development Engine for Kubernetes Tame your developer workflow to go from Code to URL in one push.
Epinio installs into any Kubernetes cluster to bring your application from source code to deployment and allow for Developers and Operators to work better together!
Related contents:
the agent-native team wiki your AI reasons over.
Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.
Persistent memory for AI coding agents One brain. Local or cloud. Agent-agnostic, single binary, zero dependencies.
Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Related contents:
mcp-beam is a MCP server (stdio transport) for casting local files and media URLs to Chromecast and DLNA/UPnP devices on your LAN.
Related contents:
An open source registry and proxy that federates MCP, A2A, and REST/gRPC APIs with centralized governance, discovery, and observability. Optimizes Agent & Tool calling, and supports plugins.
ContextForge is an open source registry and proxy that federates tools, agents, and APIs into one clean endpoint for your AI clients. It provides centralized governance, discovery, and observability across your AI infrastructure.
MCP server that turns the full ticket lifecycle into a guided conversation — no portal, no context switch, no re-typing the resource ID Azure already knows about.
Allow all your Claude Codes to message each other ad-hoc!
Let your Claude Code instances find each other and talk. When you're running 5 sessions across different projects, any Claude can discover the others and send messages that arrive instantly.
Related contents:
Subscribe once. Read by email or over MCP.
Antenna stores your feed subscriptions in one local SQLite index, then routes new posts to email and to AI agents over MCP from the same data. No vendor cloud. No proprietary lock-in. Your subscription graph lives in a file you control.
Related contents:
The Context Optimization Layer for LLM Applications
Compress everything your AI agent reads. Same answers, fraction of the tokens. Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
Related contents:
The codebase context engine your team shares.
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call-flow, interactive HTML viewer, cross-project & branch-aware search, DB/API/infra knowledge. 61% less tokens, 84% fewer calls, 37x faster. Cloud in beta.
Related contents:
The Model Context Protocol (MCP) specification is defined in the main specification repository. This repository contains extensions to the core protocol that define additional authorization mechanisms.
Related contents:
Code Intelligence Knowledge Graph for AI Coding Agents.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
The fastest, most efficient code intelligence engine for AI coding agents. It indexes any repository into a persistent knowledge graph — full-indexing an average repo in seconds and the Linux kernel in 3 minutes — so your agent answers structural questions with ~120x fewer tokens. Tree-sitter parsing across 158 languages, Hybrid LSP type resolution, single static C binary.
MCP server for Unreal Editor. Model Context Protocol server for Unreal Editor automation .
Claireon is an Unreal Engine editor plugin that runs a Model Context Protocol (MCP) server inside the editor, exposing hundreds of editor automation tools for AI-assisted development workflows behind a deliberately small MCP surface (tool_search + python_execute). It enables AI assistants like Claude Code to read, search, inspect, and edit Unreal assets directly.
This is an experimental MCP server that provides access to MDN's search, documentation, and browser compatibility data.
Our goal is to give LLMs and coding agents a reliable and up-to-date source of web platform documentation - so developers can get accurate information instead of potentially outdated content their LLMs were trained on.
Related contents:
Infobip OpenAPI MCP is a framework for exposing OpenAPI documented HTTP APIs as MCP servers. It is based on Spring AI and made to run as a Spring Boot application. It is powering Infobip's own MCP servers, and you can use it to implement your own MCP servers.
Open-source database client for PostgreSQL, MySQL/MariaDB and SQLite with SQL notebooks, visual EXPLAIN, AI and MCP built in. Hackable with plugins.
Tabularis is an open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, and SQLite, with a built-in MCP server so Claude, Cursor, and Windsurf can read your schema and run queries through the same app you already use.
🧪 Local Stack for testing Agent. MCP gateway with a built-in skill library.
One YAML. One endpoint. Every MCP server plus the skills you author alongside them.
Gridctl aggregates tools from MCP servers into a single gateway and serves Agent Skills as MCP prompts to upstream clients. Define your stack in YAML, apply with one command, and connect Claude Desktop (or any MCP client) through one endpoint.
Related contents:
Make analytics context usable by agents
ktx is an open-source context layer for data agents. It turns warehouse metadata, BI tool definitions, query history, docs, and approved metric definitions into reviewable files agents can search and execute.
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer
Open-source LLM Friendly Web Crawler & Scraper.
Crawl4AI turns the web into clean, LLM ready Markdown for RAG, agents, and data pipelines. Fast, controllable, battle tested by a 50k+ star community.
Build apps that live inside AI app. the full-stack React framework for MCP apps and MCP servers.
Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.
MCP Server for Computer Use in Windows.
Windows-MCP is a lightweight, open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server bridges the gap between LLMs and the Windows operating system, allowing agents to perform tasks such as file navigation, application control, UI interaction, QA testing, and more.
Related contents:
Your agent's query language. One SQL interface over APIs, files, and live sources — built for agents.
Coral gives agents a local-first SQL runtime over APIs, files, and other data sources. Query it from the CLI, inspect schemas and tables, or expose the same runtime over MCP so agents can use it without bespoke tool glue.
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Peekaboo is a macOS automation toolkit for humans and agents. It captures pixels, reads the accessibility tree, drives input, and ships an agent runtime plus an MCP server so AI clients (Codex, Claude Code, Cursor) can drive the desktop with the same primitives you'd use from the shell.
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read.
Semble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read and cutting latency on every step. Indexing and searching a full codebase end-to-end takes under a second, with ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality (see benchmarks). Everything runs on CPU with no API keys, GPU, or external services.
Run it as an MCP server and any agent (Claude Code, Cursor, Codex, OpenCode, etc.) gets instant access to any repo, cloned and indexed on demand.
An AI-powered environment for monitoring, managing, and troubleshooting PostgreSQL systems.
A TypeScript framework for building MCP servers capable of handling client sessions.
Persistent Memory for AI Agents. Your AI has amnesia.
Stash makes your AI remember you. Every session. Forever. No more explaining yourself from scratch.
persistent memory layer for AI agents. Episodes, facts, and working context stored in Postgres. MCP server included. Self-hosted, single binary, no cloud required.
A second brain for the AI era. Free forever.
Organize your notes as Markdown files. With native relationships, Git, and Claude Code integration.
Your entire codebase as Claude's context.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
Claude Context is an MCP plugin that adds semantic code search to Claude Code and other AI coding agents, giving them deep context from your entire codebase.
AI You Control. The Open-Source, Cross-Platform, Extensible AI Client. Choose your models. Own your data. Eliminate vendor lock-in.
Related contents:
Blender Model Context Protocol Integration.
BlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Scan your dev machine for AI agents, MCP servers, IDE extensions, and suspicious packages - in seconds.
Developer machines are the new attack surface. They hold high-value assets — GitHub tokens, cloud credentials, SSH keys — and routinely execute untrusted code through dependencies and AI-powered tools. Recent supply chain attacks have shown that malicious VS Code extensions can steal credentials, rogue MCP servers can access your codebase, and compromised npm packages can exfiltrate secrets.
Related contents:
The open source, no-code MCP Server for AI-Native API Access
Build a uniform API value chain for AI agents with secure, no-code endpoint translation across your existing API services.
reShapr is the open source, no-code MCP Server for AI-Native API Access. It bridges the gap between traditional REST/GraphQL/gRPC services and LLMs by transforming complex services into discoverable, optimized MCP tools.
Related contents:
Personal News Reader with Intelligence Training. RSS and web feeds, synced on every platform you use.
Pastebin style Kanban boards for quick collaboration. Create & share, with zero sign-up, or deploy the full version.
Self-hosted project management & issue-tracking solution + instant shareable & customizable boards + realtime collaboration, automation, API access and MCP support.
our Own AI Co-Worker. Its own computer.
Phantom deploys to a dedicated machine, learns from every conversation, and evolves its own capabilities. Open source. Self-hosted or managed.