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.
Fractal Arena
3.7/10Play Fractal Arena, a 3v3 auto-battler on Fractal Bitcoin, earn $FRACTALARENA by playing well.
Yuanzhu
3.7/10Governed AI workflow assets: staged writes, evals-gated template forging, ontology via MCP.
Prophetkey MCP
3.7/10ProphetKey MCP bridge - encrypted local-first API key vault for AI agents, keys never exposed
Glint Image
3.7/10Generate and edit images with every image model on the platform. Returns the image to the agent.
Glint Meet
3.7/10Call every global AI model through one OpenAI-compatible API. One key, all models.
Logbook MCP
3.7/10Project memory across sessions for AI agents. A queryable decision log in the repo.
Reference MCP
3.7/10Reference integrity for AI agents. Scans and verifies links, imports, assets, deps.
Release Gate MCP
3.7/10Release intelligence for AI agents. Detects breaking changes and recommends semver.
Targetly MCP
3.7/10Deployment truth verification for AI agents. Verifies the live site matches the build.
Ppsspp Dfx MCP
3.7/10Engineering-grade MCP debugging SDK turning the PPSSPP PSP emulator into an AI-debuggable target.
Grim MCP
3.7/10Security audit for AI agents: code, deps, exposure, secrets, drift, SBOM, and IoC.
Dsh Cert
3.7/10Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
Jevcore
3.7/10MCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.
MCP Server
3.7/10Audited memory over MCP: an append-only fact ledger plus verifiable invariants I1-I5.
Seocode
3.7/10Framework-aware technical SEO and AI-discoverability (GEO) audits for your codebase, in your editor.
Text Spreadsheet
3.7/10Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
Go Proxy MCP
3.7/10Go module proxy versions.
Iss MCP
3.7/10ISS live position and passes.
Openbrewery MCP
3.7/10Open Brewery DB search.
Timeapi MCP
3.7/10TimeAPI timezone conversion.
Urban Dictionary MCP
3.7/10Urban Dictionary definitions.
Usda Food MCP
3.7/10USDA FoodData Central search.
Uselessfacts MCP
3.7/10Useless Facts random facts.
Jev MCP Server
3.7/10MCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
Chartbytes MCP
3.7/10Generate chart images (bar, hbar, stacked, line, area, scatter, pie, donut) as PNG/SVG for AI agents
Kryptheon
3.7/10Record a flow through your app, check it after every change, and attack a copy of your database.
Guardian MCP
3.7/10Runtime AI-threat screening for coding agents: analyze, scan tool calls/outputs & docs (paid).
Seconded MCP
3.7/10The oracle for agents. Verify trades, tokens and messages before your agent acts.
Esq Builder MCP
3.7/10ESQ 1.0 题库包工具链(墨题刷题机):build(auto_fix) → validate(双轨校验) → upload/publish + kajweb 词表解析与热点词统计
Vaast
3.7/10Read-only access to VAAST vulnerability scan findings, workspaces, and targets for AI agents
Refreshagent
3.7/10Connect AI assistants to live Google Search Console and Analytics data through RefreshAgent.
Facebook Ads Library
3.7/10Visual MCP server for Facebook Ad Library. Search advertisers and see creatives in chat.
Linkedin Ads Library
3.7/10Visual MCP server for LinkedIn Ad Library. Search advertisers and see creatives in chat.
Tiktok Ads Library
3.7/10Visual MCP server for TikTok Ad Library. Query brands and render creatives in chat.
Limon MCP
3.7/10Free local micro-APIs: markdown cleaner, JSON validator, CSV-to-JSON, agent-config secret auditor.
Socseal MCP
3.7/10Read-only settlement proof for agents: prove a txid MINED, post-quantum signed. Fail-closed.
Snapdec
3.7/10Snap decisions for coding agents: local or hosted classify/check/score/rank via MCP.
Hamilton Harness
3.7/10Manage your Hamilton Harness AI rep: knowledge, rules, orders, tests and conversations.
Seconded MCP
3.7/10The oracle for agents. Verify trades, tokens and messages before your agent acts.
Backend Investigator
3.7/10Read-only backend diagnostics and PostgreSQL data validation with dedicated reader roles.
Videovector MCP Server
3.7/10Model Context Protocol server for the VectorMethods VideoVector media intelligence API.
Homeshed MCP
3.7/10Every tool your AI needs in one self-hosted install: memory, reasoning, git, Docker and more.
X Tkn MCP
3.7/10Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back.
Chef
3.7/10A head chef's verified answers as tools: scale recipes, fix cooking faults, swaps, yields and costs.
Chromedebug
3.7/10Record browser bugs - frames, clicks and console logs - and hand them to your AI over MCP.
Qrfile
3.7/10Send files automatically to Android over Wi-Fi, or share one-time HTTPS links and QR codes.
Token Lens
3.7/10Count and cut tokens in prompts, chats and agents for any model. Runs locally, collects no data.
Lumenhaus Energy MCP
3.7/10Read-only MCP server for Lumenhaus Energy sites, devices, charging sessions, and energy history.
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.