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.
Ferric Fred MCP
4.5/10MCP server for FRED (Federal Reserve Economic Data): full read API plus GeoFRED, 34 tools.
Ai R
4.5/10Read local AI agent sessions (Claude Code, Codex, OpenCode, Antigravity, Pi): intents, plans, tools
Explore Better
4.5/10AI-native Windows file manager for scoped discovery, disk analysis, and recoverable operations.
Adobe MCP
4.5/10Drive Adobe CC (AE, Photoshop, Illustrator, Premiere, Character Animator) from any MCP client
Panini Connector MCP
4.5/10Install + verify the panini-connector SDK on self-hosted sites, driven by AI agents.
Glade MCP
4.5/10Control the Unity and Godot editors from AI clients: scenes, scripts, physics, materials.
Docker MCP Server
4.5/10Manage Docker (containers, images, Compose, Swarm, registries) via the Docker SDK and CLI.
MCP Server
4.5/10Verify agent actions against the system of record and get signed completion receipts.
MCP Server Whoop
4.5/10Local-first, read-only WHOOP MCP server for recovery, sleep, strain, workouts, and body signals
Onec Odata MCP
4.5/10Read-only MCP server for 1C:Enterprise via OData with metadata and query builder tools.
Sysmcp
4.5/10Live Linux host signal (CPU, memory, processes, network, optional eBPF) for MCP clients.
Cryptyx MCP Server
4.5/10Institutional crypto intelligence for agents. 30 tools: signals, backtests, regime, triggers.
Bezelbub MCP
4.5/10Frame screenshots and screen recordings in Apple device bezels (device mockups). macOS only.
Smartcli
4.5/10Let agents drive vim, htop, lazygit: send keys, wait on screen state, read the rendered cell grid.
Flatcash
4.5/10Earn FLAT tokens (CPI-pegged stablecoin) by completing bounties. No wallet required.
Cascade Img
4.5/10LLM-operable Midjourney pipeline: 21 MCP tools to compose, generate, curate with vision, and log.
Stripekit
4.5/10Reconcile a declarative Stripe catalog and inspect your account — plan, push, pull, check.
Robo Cortex
4.5/10Git-aware memory store for AI coding agents; memories are anchored to git blob hashes.
Aidemo
4.5/10Narrated, captioned product-demo MP4 from a storyboard.json; re-renders itself in CI at ~$0.
Go Gerrit MCP
4.5/10Capability-gated Gerrit code review tools with opt-in review notifications pushed into the session
MCP Bastion
4.5/10Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
Karbon MCP Server
4.5/10Unofficial MCP server for Karbon practice management: contacts, work, time, invoices, payments.
Rive MCP
4.5/10Free, editor-less MCP server for Rive: create, edit, inspect, render and preview .riv animations
Pseudolife MCP
4.5/10Persistent memory for MCP-compatible agents: memory bank, fact cortex, dreams, graph.
Atheris MCP
4.5/10Country-targeted mobile/residential proxy egress for agents: live stock, proxy URLs, usage.
Evidrift
4.5/10Catch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.
Codex Tldraw MCP
4.5/10A Codex stdio MCP server that generates repo-local tldraw diagrams and detects code graph drift.
Arbitrum Transaction Preflight
4.5/10Paid Arbitrum transaction simulation and risk scoring for wallets and AI agents.
Freelance Ops MCP
4.5/10Freelance invoice ops MCP — overdue status, tone suggestion, and reminder drafts
Resume Evidence MCP
4.5/10Retrieve grounded resume evidence for a job description using BM25 + evidence reranking
Emulo
4.5/10Mine your local AI coding session logs into a profile your agent loads before every task.
Namecatcher Skills
4.5/10Score and value collectible Telegram usernames: namability 0-100, fair price, thesis. No API key.
Stillos Notary
4.5/10Signed, x402-paid StillOS notary tools: claim verdicts, OFAC screening, distress scoring.
MCP Server
4.5/10Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.
Cicd Aiops
4.5/10Governed self-managed GitLab + Gitea CI/CD ops: pipelines, runners, artifacts, RCA. 28 tools.
Identity Aiops
4.5/10Governed Keycloak + authentik identity ops: users, events, clients, MFA, RCA. 29 tools.
Minio Aiops
4.5/10Governed MinIO ops: capacity RCA, exposure audit, ILM, WORM retention, IAM, healing, 48 tools.
Proxy Aiops
4.5/10Governed Traefik + Caddy + HAProxy ops: routes, upstreams, certs, 5xx RCA. 28 tools.
Xcpng Aiops
4.5/10Governed XCP-ng ops via Xen Orchestra — 29 MCP tools with audit, budget, undo guards.
Regressguard
4.5/10Deterministic API regression checks for AI agents: snapshot a baseline, catch broken contracts.
Chinese Text Tools
4.5/10Claude Code 中文写作四合一工具箱：文本分析（字数/段落/阅读时间）、结构化大纲生成（论文/小说/商业计划书）、GB/T 7714 参考文献格式化、中文字频统计。纯本地运行。
Orcadub MCP Server
4.5/10AI video dubbing via OrcaRouter (model orca/dub): upload a video or URL, poll, download the MP4.
Omni Computer Use
4.5/10A 1:1 replica of Claude Desktop's computer-use tool surface, for Windows and the Claude Code CLI.
Seo Stack MCP
4.5/10The complete open-source SEO data stack for AI agents: 7 sources, 86 tools, one MCP server
Srdcheck
4.5/10Scoped deterministic SRD 5.2.1 rules checks for agents — applied rules cited, boundaries explicit.
Hevy MCP
4.5/10MCP server for managing workouts, routines, and exercise data through the Hevy API
Chromium Bridge
4.5/10MCP bridge between Chromium browsers (Arc, Vivaldi, Brave) and Claude Code: browser automation
Agent Receipts MCP
4.5/10EU AI Act-ready audit trail: signed, tamper-evident receipts proving what your AI agents did.
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.