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.
Promptbudget MCP
4.1/10Token-budget-aware text handling: count, truncate, and chunk for LLM prompts.
Ragdrift MCP
4.1/10Diagnose RAG drift: interpret scores, recommend thresholds, explain dimensions.
Ragmetric MCP
4.1/10RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
Shellquote MCP
4.1/10Safe shell argument escaping for bash, cmd.exe, and PowerShell.
Timezone MCP
4.1/10IANA timezone conversions with real DST rules.
Toml Yaml Json MCP
4.1/10Parse, format, and convert configs across TOML, YAML, and JSON.
Misata
4.1/10Complete package for synthetic data generation.
Gws MCP
4.1/10MCP fork of Google Workspace CLI (Gmail, Drive, Calendar, and more)
Trilium MCP
4.1/10Read and write a self-hosted TriliumNext knowledge base over its ETAPI.
Pondlog Garden
4.1/10DEPRECATED. Use @cropgraph/mcp instead. npx @cropgraph/mcp
Daimonos
4.1/10Agent-optimized MCP server with structured JSON tools. 20-45% token savings.
Kie MCP
4.1/10MCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence
Rails Agent Skills MCP
4.1/10Rails development skills, docs, and workflows exposed through MCP stdio.
Canvas MCP
4.1/10Local-first MCP server for Canvas LMS. Stdio transport, no third-party broker.
Gogcli MCP Sheets
4.1/10Extended Google Sheets for Claude via gogcli — auth + full Sheets support
Gogcli MCP Slides
4.1/10Google Slides via gogcli for Claude — deck and slide authoring
MCP Server
4.1/10Unified MCP server for Ignite UI — documentation, API, and CLI scaffolding
Tampermonkey MCP
4.1/10MCP server to manage your Tampermonkey scripts
MCP Server
4.1/10Stateful OpenAPI sandbox for AI agents to validate API integrations end-to-end.
Ead Factory
4.1/10EAD Factory MCP — Digital Trust services APIs for your agents
MCP Guardian
4.1/10Security, cost, and health governance proxy for MCP infrastructure
Gretl MCP
4.1/10Run Hansl/Gretl econometrics workflows via MCP with GUI launch and artifacts.
Fixthis
4.1/10Local-first MCP handoff for Jetpack Compose UI feedback and source candidates.
Occasio
4.1/10Tamper-evident, Sigstore-signed audit trail for Claude Code agents.
Vigil MCP
4.1/10Proactive MCP commitment tracker — the AI that reaches back out to you.
Geomelon MCP
4.1/10MCP server for the Geomelon geographic API — stdio and remote HTTP transports
MCP Server
4.1/10MCP server for the Geomelon geographic API — stdio and remote HTTP transports
Sounio MCP Server
4.1/10Check, compile, run, and test Sounio programs locally.
Knowing
4.1/10Content-addressed code graph with 22 MCP tools for AI agents.
Mchs
4.1/10Stdio MCP server for MCHS schemas, validation, support status, and evidence.
Marriage Astro
4.1/10Vedic Astrology MCP Server - birth charts, compatibility, and dosha analysis.
Playwright Trace Decoder MCP
4.1/10MCP server for unpacking and analyzing Playwright trace.zip archives
Rosentic
4.1/10Deterministic cross-branch conflict detection for AI coding agents
Rescuetime MCP
4.1/10MCP server for RescueTime productivity data
Cockpit MCP
4.1/1040 AI prompts + self-hosted ops dashboard for homelab and small-team sysadmins
Dealflow MCP
4.1/1050 AI prompts for real estate investors — BRRRR, flips, multifamily
Listingflow MCP
4.1/1050 AI prompts for real estate listing agents — CMA, MLS, buyer presentations
Contextforge MCP
4.1/10Persistent memory MCP server for Claude Code, Cursor, and GitHub Copilot.
Abs MCP
4.1/10Inspect and safely operate Audiobookshelf libraries over MCP.
Repo Memory
4.1/10Shared, git-tracked working memory for AI agents on the same codebase.
Orizn Visa MCP
4.1/10Visa requirements for 39,585 passport-destination pairs in 15 languages.
Tokeneyez
4.1/10Track every AI token across Claude, ChatGPT, Gemini, Cursor, and Claude Code.
Canvas Lms MCP
4.1/10TypeScript MCP server for Canvas LMS — 115 read+write tools across 17 domains.
MCP Server
4.1/10Entropy0 MCP server — source trust and URL safety tools for AI agents
MCP Server Apple Shortcuts
4.1/10MCP server for Apple Shortcuts via the macOS shortcuts CLI
MCP Server Fathom
4.1/10Fathom AI meeting transcription MCP server for Model Context Protocol hosts
MCP Server Freshdesk
4.1/10Freshdesk Support MCP server for Model Context Protocol hosts
MCP Server Gamma
4.1/10Gamma AI presentation generation MCP server for Model Context Protocol hosts
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.