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.
Che Ical MCP
4.5/10macOS Calendar and Reminders MCP server (29 tools). Native Swift EventKit, iCloud/Google/Exchange.
Arcade1V1
4.5/10Play 1v1 arcade games vs AI agents & humans, ranked by ELO. Replay-verified, on-chain escrow (Base).
Tsbootstrap
4.5/10Read-only time-series bootstrap server: diagnose a series and compute confidence intervals.
Heddle
4.5/10Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
Mockscreenshots MCP
4.5/10Deep links to pixel-perfect fake chat & screenshot generators (iMessage, WhatsApp & more).
Onsense
4.5/10Android phone camera, sensors & files for any MCP client — local, no cloud, no ADB.
Officeagent
4.5/10Create and edit real Word documents (filesystem or SharePoint): typed change plans, tracked changes
Openinvest
4.5/10Investment runtime for AI agents — LLM investment committee, portfolio ledger, decision accounting
MCP Launcher
4.5/10Single MCP hub: discover, add, audit, and govern MCP servers across every AI client.
Pitstop
4.5/10F1 MCP server: live timing, telemetry, standings, news, and a queryable 1950-present database.
Dify MCP
4.5/10MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients
Live Memory
4.5/10Persistent, read-only codebase memory for Claude Code; ask it instead of re-reading files.
Slang Workflows
4.5/10Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).
Smriti Memory
4.5/10Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.
Agentrisk
4.5/10Risk guardrails for AI trading agents. Your agent proposes; your policy decides.
Vouch MCP
4.5/10Sign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.
Seam Runtime
4.5/10SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
Garmin Local MCP
4.5/10Local-first Garmin data warehouse: sync once to SQLite, analyze trends and correlations offline.
MCP Egrul
4.5/10EGRUL/EGRIP company registry lookup for Russian legal entities and entrepreneurs.
MCP Fns Check
4.5/10Russian tax authority (FNS) counterparty checks: status, debts, blocks. Due diligence MCP.
MCP Sudact
4.5/10Russian court practice (Sudact): case search by article, court, dates; full decision text.
Heimdall
4.5/10Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.
Tock MCP
4.5/10Tock (exploretock.com): discover restaurants, search a city, get venue details and availability.
Viator MCP
4.5/10Search Viator tours and activities — products, availability, attractions, destinations.
Alchemy
4.5/10Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.
Freelancer MCP Server
4.5/10Search, bid, and message clients on Freelancer.com from Claude. Multi-account support.
Coverctl
4.5/10Go code coverage analysis tool with MCP server for AI-powered coverage workflows
Memini
4.5/10Local-first project memory and mistake-prevention guardrails for AI coding agents.
Stillos Notary MCP
4.5/10Ed25519-signed verdicts resolved against real external ground truth. Free, fail-closed.
Autopilot Jobhunt
4.5/10Agentic job hunt: scan careers pages, score against your resume, draft applications. Never applies.
Soldefi MCP
4.5/10Solana DeFi risk intel over x402: rug/honeypot scans, pool analysis, wash-filtered pools.
Agent Claim MCP
4.5/10File-claim coordination for parallel AI coding agents: claim files before edits, no stomping.
MCP Server
4.5/10Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE.
MCP Server
4.5/10AI-powered email & WhatsApp for teams — manage your shared inbox from Claude, Cursor or ChatGPT.
Geo Inspector MCP
4.5/10Inspect a site's AI-search readiness: AI crawler access, llms.txt, schema markup, meta directives
Supstack
4.5/10Evidence-based supplement research, dosing, safety, and interactions as agent-callable tools.
Voice Truthgate MCP
4.5/10Honest voice authenticity for AI agents: enrol a voice, verify a call clip. Signal, not verdict.
Engedi
4.5/1093 tools: finance, weather, news, travel, knowledge, SEO. 27 free + 66 paid via USDC x402.
Getregdata
4.5/10Official business-registry data - KYC/AML, UBO, credit-risk, adverse media across 11 jurisdictions.
Umbryn MCP
4.5/10Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.
Apexapi MCP
4.5/10Call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key
MCP Loom
4.5/10Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.
Getyourguide MCP
4.5/10GetYourGuide tours & activities for Claude — search, details, options, and reviews
Continuewith
4.5/10Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).
Discourse MCP Extended
4.5/10Discourse MCP server (stdio) with review-queue tools added. Fork of @discourse/mcp.
Memory Fabric
4.5/10File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.
Payfetch
4.5/10x402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.
Grad Agent
4.5/10Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking.
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.