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.
Dongbang Interior
4.1/10ABIS interior answers with cited work, exact case lookup, photo and floor-plan consulting.
Monk
4.1/10Stock research for AI assistants: scan US stocks, ETFs and futures, cite SEC filings, save queries.
Strut Stack Sql
4.5/10Token-efficient MCP server for MySQL, PostgreSQL, SQLite, DuckDB, SQL Server, and ClickHouse
Protocol Banks
3.9/10Control plane for agent money: server-enforced limits and non-custodial execution.
Killerskills
4.7/10Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Agent Data Tools Web
4.9/1026 tools: web pages, JS apps and PDFs as text, feeds, sitemaps, search. 25 free calls.
Agent Data Tools Utilities
4.9/10101 tools: JSON repair, CSV, hashes, cron, dates, units, validators. 25 free calls.
Agent Data Tools Prices
4.9/1036 tools: token prices, wallet and contract risk, liquidity pools, FX. 25 free calls.
Agent Data Tools Everyday
4.9/1018 tools: weather, time zones, sun and moon, earthquakes, countries. 25 free calls.
Agent Data Tools Compliance
4.9/1031 tools: OFAC sanctions, counterparty checks, company, domain, email. 25 free calls.
Agent Data Tools Chain
4.9/10357 tools: balances, blocks, gas, txs and logs on 5 EVM chains, plus Bitcoin. 25 free calls.
Agent Data Tools Ai
4.9/1025 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.
Agent Data Tools
4.9/10594 agent tools: chain data, prices, sanctions, web, PDF. 25 free calls, then from $0.002.
Deployangel
4.7/10Wait for production to clear each deploy, and read the evidence when a release fails.
Adb MCP
4.7/10Drive an Android emulator or device over adb: screenshot, inspect UI, tap, type, build and test.
Ufc Cards
4.1/10Find UFC cards, read saved estimates and recorded sales, and compare sales of related editions.
Temps Reel
4.9/10La Réunion (974) en direct : actualités, météo, rando, bus, eau, événements, volcan, cyclones, air.
Sysml MCP
4.7/10SysML v2 and KerML for coding agents: workspace diagnostics and edits, execution, REPL sessions.
Nestsolver
4.1/10Plan cut lists for bars and sheets, true-shape nests, and truck and pallet loads.
Identity
4.9/10Mint an agent identity in two free calls. Verify anyone. Earn 75% when someone reads you.
Twitterapi Io MCP
4.5/10Offline access to TwitterAPI.io docs for AI assistants. 67 endpoints, 32 pages, 24 blog posts.
Highwire
4.9/10Trade, launch and research higher.fun coins on Solana, from any AI agent. Unsigned or policy-signed.
Goldseam
4.9/10The U.S. Marketplace of Learning2Earning Opportunity | Sourced checklists, progress, prior learning
Cli Memo
4.7/10People's context across messengers, notes and mail, from a local store. Set up the memo CLI first.
Diffci
4.9/10Fail-closed, change-aware verification for AI coding agents with affected-test guidance.
Gmc MCP
4.5/10MIT-licensed pip-installable MCP for Google Merchant Center on Merchant API v1 (126 tools).
Tools
4.9/10764 MCP tools across 1236 fintech tools: ChainGraph AP2 decisions, execution_hash. Zero PII.
Cuttingfloor
4.9/10Hosted video editing for AI agents: cut, caption, mix and export real video. Sign in with OAuth.
Chaoscypher
4.7/10Local-first knowledge graphs from your documents: build, search (GraphRAG) and edit on your machine.
MCP Server
4.1/10Run your AI-run company from Claude Code, Codex, Cursor or ChatGPT: inbox, tasks, team, Studio.
Session Recap
4.7/10Recap AI coding sessions (Claude Code, Codex, dsh, OpenCode): intent, decisions, open threads.
Leanfare
4.5/10Makes your Claude plan last longer: hands reading and drafting to cheaper or free models.
Cyberwarex Chain Data
4.7/10Wallet balances, token prices, gas, decoded transactions and ENS on 5 EVM chains. No RPC key.
Cyberwarex Web Access
4.7/10Read any web page and search public Telegram channels, groups and bots. No API key, pay per call.
Cyberwarex Wallet Safety
4.7/10See what a transaction or signature will do before your agent signs it, plus address and link risk.
Cyberwarex Defi Oracle
4.7/10Stops your agent buying a coin it cannot sell: honeypot test, rug checks and an A-F risk grade.
Instantclips
4.9/10Create branded vertical video ads from ecommerce product URLs or product photos.
MCP Server
4.1/10Read, search and track your RSS feeds: semantic search, story clustering, watches, OPML import.
Gitmanual
4.9/10Setup manuals for any GitHub repo: will it run on macOS, Windows or Linux, and the exact steps.
MCP Server
4.9/1030 security tools for AI agents: phishing links, exposure maps, DNS, SSL, PQC, history, pivots.
Ziggs
4.9/10Lets your assistant work with the people and agents in your Ziggs workspaces: inbox, chats, tasks.
MCP Server
4.5/10Run any model on the live WaveSpeed catalog: image, video, audio, 3D.
Munim Computer Use
4.7/10Accessibility-first desktop control for any agent: background input, agent pointer, zoom, Chrome.
Api Anything
4.7/10Call websites as APIs: a shared catalog of operations learned from each site's own requests.
Plainhub
4.7/10Open files and diffs from your agent in PlainHub, and keep a shared ledger in your own GitHub repo.
Align
4.7/10Your team's confirmed decisions, with receipts, for every coding agent (local stdio server).
Bulletin
4.5/10Talk with agent swarms: rooms, private messages and paid tasks for AI agents
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.