The MCP Server Directory
Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.
What this is
The MCP Server Directory is a live, independently maintained index of Model Context Protocol servers published to the official registry. Each server is scored 0–10 on four dimensions: reliability, documentation quality, maintenance velocity, and adoption. The directory is free, updated daily, and built by MegaOne AI.
Solve
3.7/10Cloudflare Turnstile CAPTCHA solver for AI agents. $0.002/call, 100 free on signup. P95 2.2s.
Nudge MCP
3.7/10MCP server that nudges better AI session behavior through token usage and efficiency analysis
N0S1 MCP
3.7/10Secret scanner for Slack, Jira, Confluence, Asana, Wrike, Linear, Zendesk, GitHub and GitLab
Mception
3.7/10Audits other MCP servers for security risks. Returns safe / caution / unsafe / inconclusive.
Bling Bag
3.7/10Give your bot an identity!
Memforge Memory
3.7/10Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
Publicmcp
3.7/10Publish structured, AI-readable business identity data as an MCP server in minutes.
Craftyformsmcp
3.7/10Create and manage forms, collect submissions — a headless form builder powered by CraftyForms.
Crafty Form Server
3.7/10Create and manage forms, collect submissions — a headless form builder powered by CraftyForms.
Cait
3.7/10Core AI Toolkit - a modular MCP server that extends AI assistants with practical capabilities
Docker Wts Build
3.7/10Schedule Docker builds via Windows Task Scheduler — survives VS Code terminal timeouts
Cognirelay
3.7/10Self-hosted agent continuity server with bounded, recoverable memory and restart orientation.
Playwright MCP
3.7/10Playwright Tools for MCP
Agentbill MCP
3.7/10Billing infrastructure for AI agents. Preflight spend checks + post-execution usage billing.
Lsp MCP
3.7/10Universal LSP MCP server
Proofstream MCP
3.7/10Dispatch a human verifier to physically verify anything in the real world. For AI agents.
Five MCP
3.7/10160K deductive JSON constraints enforce LLM character consistency — eliminate persona drift.
Google Workspace
3.7/10Give AI agents access to Gmail, Calendar, Drive, and more — multi-account, manifest-driven
Claudetest
3.7/10Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.
Aws MCP
3.7/10AWS MCP server — call any AWS API from AI assistants, with first-class SSO re-login
Ctxlint
3.7/10Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
Electron MCP
3.7/10Electron.js MCP server — IPC scaffolding, security auditing, build tooling for AI assistants
Fetch MCP
3.7/10HTTP fetch MCP server: SSRF protection, HTML-to-markdown, reader mode, metadata extraction
Npmjs MCP
3.7/10npm registry MCP server — package intelligence, security audits, dependency analysis
Postgres MCP
3.7/10PostgreSQL MCP server - query, schema introspection, explain, and health checks for AI assistants
Dpx
3.7/10AI oracle + settlement rail. Macro/ESG/climate intelligence, x402 pay-per-call, USDC/EURC on Base.
Atomadic Fuse
3.7/10Atomadic Fuse MCP — polyglot compiler, harvest logic atoms, discover product chains.
Atomadic Nexus
3.7/10Atomadic Nexus — trust layer for the agent economy. 32 tools: trust gates, x402, lineage, swarm.
MCP Ezpath
3.7/10Base DEX meta-router. Races 0x, ParaSwap, Aerodrome & Uniswap V3. Best quote. X402 pay-per-use.
Folosat MCP
3.7/10Folosat MCP — income allocation, savings goals, group expenses and wealth tracking. EN & AR.
MCP Server Innoday
3.7/10Unified ticketing MCP server for Jira, Linear, Trello, Notion, and GitHub Issues.
Fast Html MCP
3.7/10Lightning-fast HTML generation from AI agents with 15 tools, 22 components, and 25 templates.
Linkguard MCP
3.7/10Backlink tools for AI assistants: redirect, Google index, and backlink health checks.
Razorpay
3.7/10MCP server for Razorpay API.
Ctnp MCP
3.7/10Ingeniux CTnP MCP server for personalization, A/B testing, and audience management.
Modelrisk MCP
3.7/10Read, build, fit, and run Monte Carlo risk models in Excel through Vose Software's ModelRisk.
Unlimited MCP
3.7/10Delegate coding and sysops tasks to cheaper agents or local LLMs via durable background job queues.
Dockase Legal MCP
3.7/10Nigerian & Commonwealth legal reasoning, RAG search, contract analysis, and citation verification.
Agent Wallet
3.7/10Governed USDC wallet for AI agents — daily cap, allowlist, step-up, and tamper-evident receipts.
Test MCP Server
3.5/10Alpic Test MCP Server - great server!
MCP Server
3.5/10Public MCP server for the LLM Search Engine
MCP Server
3.5/10Search and browse a curated gallery of memes, infographics, and visual content.
Meminal
3.5/10Memory for deep conversational context across any platform
MCP Merchant
3.5/10Search-only commerce MCP server backed by Stripe (test)
MCP Registry
3.5/10Search the public MCP Registry; discover servers and copy SSE URLs.
MCP Server
3.5/10Deploy sims to any screen. Control your displays with Claude.
MCP Server
3.5/10Deploy sims to any screen. Control your displays with Claude.
Server
3.5/10Create and manage your own Certificate Authority for internal HTTPS.
Free · No spam
New servers, score changes, breakages
Every Monday: what shipped, what broke, what's worth trying. Five minutes. No filler.
Four dimensions, weighted
- Reliability (30%) — repository present, permissive license, not archived, official status.
- Documentation (20%) — description length, website presence, README quality.
- Maintenance (25%) — how recently the code was pushed; versioning discipline.
- Adoption (25%) — GitHub stars (log-scaled), remote availability, official endorsement.
What is MCP?
MCP stands for Model Context Protocol. It is an open standard introduced by Anthropic in late 2024 that lets AI assistants like Claude connect to external tools, data sources, and services through a common interface. An MCP server is a small program that exposes one capability (file access, a database, an API) to any MCP-compatible AI client.
Where does the data come from?
Every server in this directory is pulled from the official Model Context Protocol Registry at registry.modelcontextprotocol.io. We also enrich each entry with GitHub metadata (stars, last commit, license, primary language) where a repository is linked. The full re-scan runs daily.
How are servers scored?
Each server gets a 0–10 overall score, weighted from four sub-scores: reliability (30%), documentation (20%), maintenance (25%), and adoption (25%). The full methodology is visible on this page under "How scoring works".
Is this affiliated with Anthropic?
No. MegaOne AI is independent. Anthropic created the MCP standard and maintains the reference implementations, but this directory is built separately and rates all servers including Anthropic's own.
How often does the directory update?
The pipeline re-fetches the full registry and re-scores every active server once per day. Individual entries are refreshed whenever a new version is published to the official registry.
Is it free?
Yes. Browsing, filtering, and searching the directory is free. The weekly email briefing is free. There is no account required.