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.
Anki MCP Server
8.1/10A Model Context Protocol (MCP) server that enables AI assistants to interact with Anki, the spaced repetition flashcard application.
Auxen
5.6/10Provision private AI model endpoints on dedicated GPUs (Llama, Qwen, Mistral). Pay per minute.
Openai Tools
4.9/10Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.
Game Assets
4.9/10Generate game assets with AI: sprites, 3D models, animations, sound effects, music, and voices.
MCP Server
4.9/10Remote MCP Server that securely connects Glean Enterprise Knowledge with your IDE, LLM, or agents.
Justcall MCP Server
4.9/10JustCall MCP Server enables LLMs and AI agents to make voice calls and send SMS via JustCall APIs.
MCP Server
4.9/10Manage, version, and publish LLM prompts with blocks, variables, and evaluations.
MCP Server
4.9/10AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified.
Tenzro
4.9/10Tenzro Ledger MCP: wallet, identity, payments, inference, staking, bridges, verification, agents.
Orggen
4.9/10Generate org charts, MCD/ERD data models, and C4 architecture diagrams — pilot OrgGen AI via MCP.
Xfms
4.9/10Pick the right LLM for any task. Ranked shortlist with rationale across 8 evaluators.
Vehicle Recalls
4.9/10Check U.S. NHTSA vehicle safety recall campaigns by make, model, and year. Live official data.
Savvly
4.9/10Savvly MCP: query fund data, model projections, and compare against alternative retirement products.
Stealth
4.9/10Zero-storage MCP privacy proxy — PII tokenized before AI inference. ML-DSA-65 signed, Base-anchored.
Doom
4.9/10Obsolescence-risk screening: predicts if a product gets absorbed into core LLM-platform features.
World Model
4.9/10Event-sourced world model for multi-LLM agents: propose, validate, and read a shared state.
Connect
4.9/10Governed personal world model and memory for your AI agent. Pair once, connect over MCP.
Snow
4.9/10Live ski snow, multi-model forecasts, powder rankings & a grounded Answer Engine for 500+ resorts.
MCP Server
4.9/10Spot market for AI inference tokens. Buyers pay per draw in USDC on Base; sellers host delivery.
Rubrkit
4.9/10MCP-native AI evaluation: rubric audits, eval suites, and proof reports for AI/LLM output.
Modelmeter
4.9/10The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events.
Hunchful
4.9/10Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).
Cleanor
4.9/10Zero-auth MCP: image optimize, cited storage/format data, and dev utilities LLMs get wrong.
Agent Ready Kit
4.9/10Agent-readiness scanner (0-5 score), robots.txt + llms.txt generators, managed agent enablement.
MCP Server
4.9/10Run 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing.
Fitllm
4.9/10Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
Ai Crawler Robots Monitor
4.9/10Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes.
Ai Rete Rag MCP
4.9/10Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
Evals
4.9/10Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Llm Latency Tracker
4.9/10Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.
Boundaryai
4.9/10Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Groundtruth
4.9/10Two independent AI models read a GPR, locate or pipe scan and flag the do-not-core call.
MCP Server
4.9/10Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
Enricher
4.9/10Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
Model Lifecycle
4.9/10Check whether an LLM model id is deprecated, retiring, or retired, and what to migrate to.
Ai Netcafe
4.9/10Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.
Mdkit
4.9/10Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Commercial
4.9/10Discover DigitalPublic plans, trust, ROI, status and autonomous Sandbox enrollment for AI agents.
Dcl Trust Oracle
4.9/10AI/LLM agent output audit MCP: policy eval, tamper-evident chain, AI safety, x402 USDC on Base.
Aio
4.9/10AI integrity standards, benchmarks, and EU AI Act-aligned Tier 0 model certification
Living Memory
4.9/10An MCP memory server. One memory your agents share — across models, devices and apps.
MCP Server
4.9/10Audit a site's structured data and llms.txt, match a trade to a template, and quote real prices.
MCP Server
4.9/10Generate images with any major model — one API key, one prepaid balance, one MCP.
Unreal MCP Server
4.7/10A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Metehangzl Pokemcp
4.7/10Provide detailed Pokémon data and information through a standardized MCP interface. Enable LLMs an…
Scrapegraphai Scrapegraph MCP
4.7/10Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
Alex Llm Attack MCP Server
4.7/10Query and retrieve information about various adversarial tactics and techniques used in cyber atta…
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.