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.
Agent Q
4.3/10Local MCP server for requesting signatures from Agent-Q Firmware.
Claude Faf MCP
4.3/10Persistent project context for Claude. IANA-registered .faf format.
T1 T2 Protocol
4.3/10Caller-side T1/T2 heterogeneous validation MCP server. Stdlib-only Python.
X402 Trust MCP
4.3/10Trust & reliability data for x402 endpoints before your agent pays them.
Accint
4.3/10Local Work Model MCP server for agent work that learns from real outcomes.
Codex Control Plane MCP
4.3/10Durable MCP control plane for long-running Codex Desktop tasks.
Retro MCP
4.3/10Data-grounded sprint retrospectives from your Jira, GitHub, and Slack activity.
Standup MCP
4.3/10Generate your daily standup from real GitHub, Jira, Linear, and Slack activity.
Tapd MCP Server
4.3/10在 Cursor/Copilot 中查询、分析和回填 TAPD bug / 需求
Uindow
4.3/10Real signed-browser automation for AI agents, over a local stdio MCP server.
Topos
4.3/10Structural code-quality tools for AI coding agents.
Hone
4.3/10Score your judgment over AI-assisted work. Hone scores you, not the model.
Kreuzcrawl
4.3/10Scrape, crawl, and map websites to Markdown or JSON via local CLI.
MCP Server Cal
4.3/10Cal.com scheduling MCP server: manage bookings, event types, and availability.
Karst
4.3/10Code context for AI dev tools: pack-scoped, cited code retrieval over MCP.
Arc 1
4.3/10MCP server for SAP ABAP systems
Beckett Godot MCP
4.3/10MCP server embedded in the Godot 4 editor; drive Godot with AI, zero sidecar.
Familiar MCP
4.3/10MCP server that drives the user's real macOS Chrome via AppleScript. 32 tools.
Forensic Deepdive
4.3/10Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
Ai Connector For Revit
4.3/10+50 tools to inspect, select, edit and document elements in live Revit models.
Intel MCP
4.3/10Coin smart-money scores, wallet reputation, signal feeds, and KOL leaderboards.
Monet
4.3/10Local-first, state-centric memory for coding agents. MCP server + CLI.
Anaconda MCP
4.3/10Beta conda env/package MCP server; requires conda, auth, and Beta Terms.
File Ai
4.3/10Agent-ready local document context with stable anchors.
Scaleway MCP
4.3/10Scaleway MCP server for interacting with the Scaleway APIs
MCP Server Openshift
4.3/10OpenShift/Kubernetes cluster management via the oc CLI for MCP clients
Ovellum
4.3/10Auto, manual, or hybrid docs that never fall out of sync.
Crawlberg
4.3/10Scrape, crawl, and map websites to Markdown or JSON via local CLI.
Zenith
4.3/10Author, validate, edit, and render deterministic .zen design docs to PNG/PDF.
MCP Broker
4.3/10Local MCP broker that exposes one compact entry for many upstream servers.
Logodev MCP
4.3/10Look up company logos and brand data via the logo.dev API.
Trestle
4.3/10Detects leaked secrets (API keys, tokens, private keys) in source code.
Bounded Tools MCP
4.3/10Read-only MCP server over bounded.tools's Sigstore-verified static API (stdio).
Grok Faf MCP
4.3/10Persistent project context for xAI Grok. IANA-registered .faf format.
Parseur Py
4.3/10Manage Parseur.com mailboxes, parser fields, documents, exports and webhooks.
Sipnav MCP
4.3/10MCP server for the SIPNAV VOIP switch.
Droste Memory
4.3/10Local code-memory graph for AI coding agents.
Reel Estate MCP
4.3/10Turn real-estate listing photos into property videos from your AI assistant.
Delx Agent Utilities
4.3/10Stateless URL, DNS, x402, JWT, encoding, and parsing tools for AI agents.
Wellness Cycle Coach
4.3/10Local-first cycle coach MCP for phase-aware nutrition and training context.
X402 Notary MCP
4.3/10Cryptographic receipts for AI outputs on Base or Solana via x402.
Fabric Dw MCP
4.3/10MCP server for Microsoft Fabric Data Warehouses and SQL Analytics Endpoints
Governance MCP
4.3/10AI governance evidence for EU AI Act, ISO 42001, SOC 2, and NIST AI RMF.
Spudcoach
4.3/10Deterministic Brotato theorycrafter MCP server: facts and math, not guesses.
Xbbg MCP
4.3/10Local Bloomberg tools for xbbg users.
Devtime
4.3/10Local-first, read-only MCP server for evidence-backed repository memory.
Engineering Board
4.3/10Repository-owned engineering pattern intelligence - 19 MCP tools over stdio.
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.