Collection · 88 entries
MCP servers and Model Context Protocol tools
Production MCP servers, gateways, frameworks, and clients - everything in this directory that speaks the Model Context Protocol.
MCP went from spec to ecosystem fast. The tools here split into a few clear shapes: servers that expose data or actions to agents (Prometheus, Figma, codebase intelligence), gateways and aggregators that consolidate many servers behind one endpoint (1mcp), clients and CLIs that let you call MCP tools from a shell (mcpc, mcp2cli), frameworks for building production servers (Golf), and benchmarks for stress-testing them (MCPMark).
If you're new to MCP and want a starting point, look at the codebase intelligence ones (Qartez, codebase-memory-mcp) - they're the most concrete demonstration of what an MCP server actually changes about the agent loop.
trace-mcp - framework-aware codebase MCP for coding agents
MCP server with 138 tools and cross-language framework awareness (58 integrations across 81 languages). Indexes Laravel/Inertia/Vue, Rails/Hotwire, Django/HTMX edges so agents skip re-deriving call graphs. Decision memory links architectural choices to the code they're about. Local-first ONNX embeddings, optional LSP enrichment.
mcptube - Karpathy-style LLM wiki for YouTube
MCP server that turns YouTube videos into a persistent, merging wiki rather than ephemeral vector chunks. Scene-change frame extraction + vision analysis captures slides, code, and diagrams that transcripts miss. 25+ MCP tools, FTS5+LLM hybrid retrieval, version history with source attribution per claim.
ThinkWatch - enterprise AI and MCP bastion host
Rust gateway in front of OpenAI, Anthropic, Gemini, and self-hosted LLMs (plus MCP servers) with RBAC, audit logs, rate limits, and cost tracking. The boring layer enterprises actually need.
OpenTabs - API-driven browser agent
Chrome extension and MCP server that lets coding agents drive web tasks by calling site APIs instead of clicking through the DOM. Targets the brittleness of Playwright-style browser automation.
agent-browser-mcp - real Chrome control over MCP
MCP server that drives an actual Chrome instance via the Chrome DevTools Protocol with page scanning, screenshots, and physical input simulation for agents.
anything-analyzer - protocol analyzer with MCP
All-in-one network protocol toolkit with browser capture, MITM proxy, JS hooks, fingerprint spoofing, and an MCP server so agents can drive the analysis directly.
Security-Detections-MCP - detection engineering over MCP
MCP server tailored for defenders - exposes detection-engineering primitives so agents can author, refactor, and validate SIEM/EDR detections.
asynkor - file leasing for AI agent teams
Go MCP server that gives multiple agents (or IDEs) leases on files so concurrent edits don't trample each other - a Git-free way to avoid merge conflicts in multi-agent runs.
codex-mcp-server - call Codex from Claude Code
MCP wrapper around the OpenAI Codex CLI that lets Claude Code (or Cursor) hand specific tasks to Codex as a sub-agent over MCP.
OQP - verification protocol for AI agents
MCP-compatible spec defining four endpoints (capabilities, workflows, execute, assess-risk) so agents can prove a shipped change satisfies business requirements before it goes live.
mcp-shark - Wireshark for Model Context Protocol
Electron capture and inspection tool for Model Context Protocol traffic. Records every HTTP request/response between an IDE and its MCP servers for forensic analysis.
idea-reality-mcp - prior-art MCP for coding agents
MCP server that scans GitHub, Hacker News, npm, PyPI, and Product Hunt before an agent starts building, surfacing whether the idea already exists and at what scale.
VTCode - Rust TUI coding agent with multi-provider support
Ratatui-based coding agent with Anthropic, OpenAI, Gemini, and Codex providers, plus local LM Studio/Ollama. Uses ast-grep for structured code search and supports MCP and Agent Client Protocol.
OpenYak - local BYOK alternative to Claude Code
MIT desktop agent for Windows/macOS/Linux with 20+ tools, MCP support, Ollama, and 100+ models via OpenRouter. No telemetry, fully local execution loop.
mcpm.sh - MCP package manager and registry
Cross-platform CLI to search, install, and configure MCP servers across Claude Desktop, Cursor, Cline, Continue, Goose, and more. Includes router and profile features for routing requests across servers.
Graph-Hub - codebase as queryable knowledge graph
Local-first code intelligence layer that turns a codebase into a Kuzu-backed knowledge graph for Claude Code, Cursor, and other MCP clients. Reports up to 85% token savings vs grep-style retrieval.
lean-ctx - MCP context optimizer for AI coding agents
Rust MCP server plus shell hook that compresses context for Cursor, Claude Code, Copilot, Windsurf, Gemini CLI and 24 other tools. Single binary, zero telemetry.
mcp-shodan - Shodan MCP server for AI agents
MCP server exposing Shodan APIs for IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Plugs into Claude Code, Codex, Gemini CLI, and Claude Desktop.
byob - bring your own browser to AI agents
Chrome extension and MCP bridge that lets your AI agent drive the Chrome you already have open, including authenticated sessions. Works with Claude Code and Cursor.
stash - persistent memory layer for AI agents
Self-hosted single-binary Go service that stores episodes, facts, and working context for AI agents in Postgres. Ships an MCP server and runs without cloud dependencies.
claude-code-organizer - dashboard for CC configs
npx dashboard to manage Claude Code memories, configs, and MCP servers. Includes a tool-poisoning scanner, context token budget tracker, duplicate cleanup, and scope management.
lilith-zero - Rust security runtime for MCP
Transport-layer security middleware for LLM agent systems that enforces deterministic policies to mitigate data exfiltration and unauthorized tool calls. OS, language, and framework agnostic.
Wax - on-device RAG memory layer in Swift
Single-file Swift memory layer with sub-millisecond RAG on Apple Silicon via CoreML and Metal. No server, no API, ships an MCP server out of the box.
token-ninja - local shell command router for AI tools
MCP-fronted router that runs deterministic shell commands locally with ~19us latency, bypassing the LLM entirely. Cuts token spend on routine commands inside Claude Code, Codex, Cursor, and Copilot.
MicrosoftDocs/mcp - official Microsoft Learn MCP server
Microsoft's official MCP server and CLI that exposes Microsoft Learn docs and code samples to LLMs and AI agents in real time.
Pare - token-efficient MCP servers for dev tools
Set of structured, token-efficient MCP servers for git, test runners, npm, and Docker designed specifically for agent consumption rather than human readability.
pipelock - MCP firewall for AI agents
Go-based agent firewall that controls egress from MCP servers, blocking SSRF, DLP leaks, and prompt-injection vectors at the network layer. Acts as a fetch proxy for tool calls.
MCPJungle - self-hosted MCP gateway
Go gateway and registry that lets individuals and teams run a single MCP endpoint in front of many backend MCP servers, with discovery and access control built in.
simulink-agentic-toolkit - Simulink MCP and skills
Official MATLAB toolkit that gives AI coding agents tools and domain knowledge for Simulink and Model-Based Design via an MCP server plus Codex/Claude Code skills.
vurb.ts - Express.js for MCP servers
TypeScript framework for building MCP servers with type-safe tools, presenters that control what the LLM sees, and built-in PII redaction. Targets Claude Code, Cursor, and other MCP clients.
Lightport - OpenAI-compatible LLM gateway
Open-source AI gateway that makes any LLM provider OpenAI-compatible, originally a Portkey fork hardened around the MCP ecosystem at Glama.
Mulder - MCP server for digital forensics
Containerized MCP server that exposes Volatility, Sleuthkit, Plaso, and other forensic tools as typed tool calls, with append-only audit log and citation-backed findings.
claude-historian-mcp - search past Claude Code chats
MCP server that indexes Claude Code conversation history and exposes it as a searchable tool. Lets agents recall what was decided in past sessions instead of re-deriving it.
Aegis - runtime policy enforcement for AI agents
TypeScript policy engine that wraps agent execution with cryptographic audit trails, human-in-the-loop approvals, and a kill switch, with no code changes to the agent itself.
forgemax - sandboxed local MCP gateway
Rust MCP gateway that collapses N servers and M tools into two tools by following the Code Mode pattern, cutting tool-list overhead to roughly 1,000 tokens.
kordoc - HWP/HWPX/PDF/XLSX/DOCX to Markdown
CLI and MCP server that parses Korean office formats (HWP, HWPX) along with PDF, XLSX, and DOCX into Markdown for agent consumption. Targets Korean document workflows that other parsers skip.
cupertino - Apple Docs MCP server in Swift
Local crawler and MCP server for Apple Developer Documentation, written in Swift. Lets agents query iOS, macOS, and Swift framework docs offline.
GoPeak - MCP server for Godot Engine
MCP server with 95+ tools for Godot: scene management, GDScript LSP, DAP debugger, screenshot capture, input injection, ClassDB introspection, and a CC0 asset library. Run via npx for any MCP client.
korean-law-mcp - Korean legal data MCP
MCP server that maps 41 Korean government legal APIs to 16 agent-friendly tools, with a citation-verification layer that guards against LLM hallucinations on case law. Covers statutes, precedents, ordinances, and treaties.
mcp-cli - low-overhead MCP runner in Rust
Rust CLI that runs MCP servers with reduced fork/exec overhead, intended for AI coding agents that spawn many short-lived MCP calls. Cuts the per-tool-call cost of MCP-heavy workflows.
antigravity-link-extension - mobile bridge for Antigravity IDE
Chrome extension that mirrors Google's Antigravity IDE sessions to your phone, lets you send messages, stop generation, and automate via 9 MCP tools or OpenAPI. Brings remote control to a closed IDE.
gopher-mcp - C++ SDK for MCP
Model Context Protocol implementation in C++ with async transport, JSON-RPC, and security primitives. Targets MCP servers that need native performance or embed into existing C++ stacks.
arbor - graph-native code intelligence
Rust code intelligence engine that builds a deterministic program graph for agents instead of relying on embedding-based RAG. Exposed over MCP for Claude Code and similar clients.
cs - CLI code search with structure-aware ranking
Go CLI code search tool that understands code structure and ranks results by relevance. No indexing required; ships CLI, TUI, MCP, and HTTP modes from a single binary.
keeper.sh - universal calendar MCP server
Self-hosted calendar sync tool and MCP server that aggregates Google, Outlook, Office 365, iCloud, CalDAV, and ICS into one feed. Lets agents read and write across every calendar from a single MCP endpoint.
figma-ui-mcp - draw and read Figma from agents
MCP server that lets Claude Code, Cursor, VS Code, and Windsurf draw UI directly on the Figma canvas via JavaScript and read existing designs back as structured data. No Figma API key required.
repowise - codebase intelligence over MCP
Python tool exposing auto-generated docs, git analytics, dead-code detection, and architecture decision records over MCP. Designed for teams running Claude Code at scale.
grafbase - GraphQL federation gateway
Rust GraphQL federation gateway with first-class MCP support, letting agents call federated subgraphs as tools. Acquired by The Guild but still open source.
routiium - LLM gateway with tool-result guard
Self-hosted, OpenAI-compatible LLM gateway that guards not just user prompts but tool return values - the harder injection surface in agent loops with web fetch, MCP, and shell tools.
web-agent-protocol - record and replay browser MCP
MCP server that records user browser interactions and lets agents replay them as automation scripts. Bridge between human demonstrations and agent execution.
concierge - SDK for building MCP servers
Python SDK for authoring MCP servers with batteries for tool registration, auth, and apps-sdk style flows. Aims to be the universal scaffold for new MCPs.
octocode-mcp - semantic code search MCP server
MCP server that lets agents search public and private GitHub repos with natural-language queries, find real implementations, and pull code context into the model.
drift - codebase pattern memory MCP server
MCP server and offline CLI that detects codebase patterns and conventions and remembers architectural decisions across sessions, so agents stop drifting from house style.
MemoMind - local GPU-accelerated memory for Claude Code
Local-first memory system for Claude Code with GPU acceleration and zero cloud dependency. Provides persistent agent memory via MCP.
Nexus - governance gateway for LLM and MCP traffic
Rust gateway that fronts LLMs and MCP servers with policy enforcement and observability. Aimed at securing agent traffic in larger deployments.
vibe-check-mcp - mentor feedback for agents
MCP server that gives agents mid-task mentor feedback to break tunnel-vision, over-engineering, and reasoning lock-in. Targets long-horizon coding workflows.
mcp-redis - official Redis MCP server
Redis's official MCP server, exposing data management and search over Redis to agentic apps as natural-language tool calls.
vestige - cognitive memory MCP server
Single-binary Rust MCP server that gives agents long-term memory via FSRS-6 spaced repetition, 29 cognitive modules, and a 3D dashboard. Works with Claude, Cursor, JetBrains.
atlas-mcp-server - Neo4j task system for agents
MCP server backed by Neo4j that gives LLM agents project, task, and knowledge tiers for managing complex multi-step workflows, with deep-research mode.
mcp-hub - centralized MCP server manager
Central manager for MCP servers with dynamic start/stop, health monitoring, and aggregated tool listing. Useful when juggling many MCPs across IDEs.
webclaw - local-first web extraction for LLMs
Rust CLI, REST API, and MCP server for fast local web scraping, crawling, and structured extraction. Positioned as a self-hosted Firecrawl alternative.
cordum - agent control plane with policy gates
Open agent control plane in Go that enforces pre-execution policy, approval gates, and audit trails over LangChain, CrewAI, MCP, or any framework.
mcpc - CLI client for MCP servers
CLI client for MCP with persistent sessions, stdio and HTTP transports, OAuth 2.1, JSON output for code mode, and a sandbox proxy. Useful for scripting and CI.
claude-delegator - delegate to Codex and Gemini from Claude Code
MCP plugin that lets Claude Code delegate subtasks to Codex and Gemini directly inside a session. Useful for cross-model orchestration.
onecli - credential vault for AI agents
Open-source credential vault that gives AI agents access to third-party services without exposing raw API keys. MCP integration for Claude Code and similar agents.
mcp-nixos - MCP server for NixOS resources
Model Context Protocol server that exposes NixOS packages, options, and Home Manager resources to agents. Useful for Nix-heavy dev environments.
stealth-browser-mcp - anti-bot browser automation MCP
MCP server that drives a Chrome devtools session past anti-bot systems. Lets agents write network hooks and clone UIs from natural language.
kmcp - Kubernetes controller for MCP servers
Go CLI plus Kubernetes operator that builds, tests, and deploys MCP servers as native k8s workloads. Wraps server lifecycle in standard kubectl-style flows.
awesome-mcp-devtools - curated MCP devtool index
Curated list of SDKs, libraries, gateways, and testing utilities for building and shipping Model Context Protocol servers. Focused on developer tooling, not server inventories.
open-harness - composable SDK for AI agents
TypeScript SDK for building agents with a code-first composition model: tools, skills, and MCP servers wire together as plain modules. Ships an agent loop you control.
lunar - agent-native MCP gateway
MCP gateway focused on governance and security: policy enforcement, request inspection, and rate-limiting between agents and MCP servers. Sits between the model and the tool surface.
google-docs-mcp - Google Docs MCP that actually works
MCP server for Google Docs that uses pattern-matching search-and-replace (like file editors) instead of character offsets, which LLMs are notoriously bad at. Fixes the broken existing options.
Qartez MCP - codebase intelligence for AI agents
Rust MCP server that pre-indexes a codebase with PageRank, blast-radius, git co-change, and complexity signals. Agents query the graph instead of grepping files.
AgentShield - security scanner for AI agents
CLI, GitHub Action, and GitHub App that scan agent configs, MCP servers, and tool permissions for vulnerabilities. Detects skill poisoning and prompt-injection vectors.
Open Cowork - desktop app for AI coding agents
Open-source Windows/macOS desktop that one-click installs Claude Code, MCP tools, and Skills with sandbox isolation, multi-model support, and Slack/Feishu hooks.
AIMock - mock everything your AI app talks to
One package, one port, zero deps to fake LLM APIs, MCP servers, A2A, AG-UI, vector DBs, and search backends in tests.
Oxideterm - all-in-one terminal workspace
Native Rust + Tauri 2 terminal with local shells, SSH, SFTP, remote IDE, AI agent, MCP, RAG, and a file manager - all in one binary. No OpenSSL dependency.
1mcp - unified MCP server aggregator
Aggregates many MCP servers behind one endpoint. Acts as an MCP gateway/proxy so clients only configure a single server.
Prometheus MCP server
MCP server that lets agents query and analyze Prometheus metrics through a standardized tool interface. Useful for ops-aware coding agents.
mcpc - universal CLI for MCP
MCP client with persistent sessions, stdio + HTTP transports, OAuth 2.1, JSON output for code mode, and a sandbox proxy. Calls any MCP server from a shell.
MCPMark - stress-testing MCP benchmark
Benchmark harness that evaluates models and agents on real-world MCP usage. Comparable scores across servers and frontier models.
mcp2cli - turn any MCP/OpenAPI/GraphQL server into a CLI
Runtime adapter that exposes any MCP, OpenAPI, or GraphQL server as a flat CLI. Zero codegen, zero rebuild - handy for shell scripts and agent toolchains.
awesome-harness-engineering - agent harness toolkit
Curated awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
AgentKit - multi-agent networks in TypeScript
Inngest's framework for multi-agent networks with deterministic routing and MCP-native tooling. Picks up where the LangGraph/CrewAI camps trail off.
Amazon Q Developer CLI
Agentic chat for the terminal - natural-language workflows wired into shell, MCP servers, and AWS tooling. Linux/macOS native, Rust binary.
codebase-memory-mcp - fast code intelligence MCP
MCP server that indexes a codebase into a persistent knowledge graph in milliseconds. 66 languages, sub-ms queries, single static binary.
Golf - production MCP server framework
Build, deploy, and scale MCP servers with auth, observability, debugging, telemetry, and a runtime baked in. Skips the per-server boilerplate.
figma-mcp-go - Figma MCP for free users
Go-based MCP server that gives agents read/write Figma access without rate limits. Text-to-design and design-to-code in one binary.
Frequently asked
What is the Model Context Protocol?
MCP is an open protocol from Anthropic that standardizes how LLM applications connect to external data sources and tools. An MCP server exposes capabilities (read data, run commands) that any MCP-aware client can call without per-integration glue code.
Do I need to build my own MCP server?
Often no - start with existing servers (codebase intelligence, Prometheus, Figma) and aggregators (1mcp). Build your own when you have proprietary data or a domain-specific action that no off-the-shelf server covers.
How do I evaluate which MCP server actually helps my agent?
MCPMark benchmarks server-and-model pairs on real-world tasks. For your own setup, the practical signal is whether the server reduces tool-call rounds or context bloat versus a baseline of grep/curl.
Related collections
Claude Code tools, plugins, and integrations
The best tools, MCP servers, and harnesses for getting more out of Claude Code - orchestration, observability, telemetry, and remote control.
Security tools for AI coding agents
Sandboxes, scanners, proxies, and governance toolkits that keep autonomous agents from doing damage.