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.
Rostro
4.7/10Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more.
MCP Server
4.7/10MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
Roundtable
4.7/10Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
MCP Server
4.7/10MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
Driftoracle
4.7/10DriftOracle - 15 tools for model/data drift monitoring: PSI, KS-test, alerts, evidence packs.
Sentinelx
4.7/10Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Options Analysis Suite MCP
4.7/10Options analytics: 17 pricing models, 17 Greeks, GEX, IV, 23 screeners, unusual, dark pool, max pain
MCP Server
4.7/10Connect AI assistants to your product operating model — OKRs, strategy, and discovery.
Api MCP
4.7/10Gateway between LLM agents and world data through eight tools and a bundled endpoint catalog.
Aigist
4.7/10Publish & manage shareable HTML/Markdown pages from your LLM, with access control.
Concordance
4.7/10Deterministic claim verification with receipts across ~60 domains. No model in the loop.
Census
4.7/10List reverse-ETL sources, destinations, models, syncs and runs; trigger syncs into SaaS tools.
Trading MCP
4.7/1072 x402 endpoints: trading, AI inference, blockchain, escrow. USDC on Base+Solana.
Make Effects
4.7/10Generate reproducible image, video, and audio assets with leading models and your own provider keys.
Cluster MCP
4.7/10Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.
MCP Server
4.7/10MCP server for Tessera's LLM cost-optimization layer: anchored spend, drift, recommendations.
MCP Server
4.7/10Pay-per-call AI + web + on-chain tools over x402 (USDC on Base): LLM, SEO, extract, token safety.
Mockserver
4.7/10Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
Council
4.7/10Multi-model consensus: 2-6 frontier LLMs answer, an independent judge synthesises one answer.
MCP Model Router
4.7/10MCP server for the @agentutility model-router cluster — pay-per-call x402 tools, no API keys, USDC…
MCP Server
4.7/10Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
Animica
4.7/10Animica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.
Districtapi MCP
4.7/10US public school districts and schools by address — enrollment, demographics, boundaries
MCP Server
4.7/10Was this document edited, did its redactions hold, is it safe for a model to read — Tamperlens API.
Weckr
4.7/10Ask which of your customers cost more in LLM calls than they pay, per user and per feature.
Video
4.7/10Compose and render video from one JSON template. Deterministic, runs locally, no generative model.
Animica
4.7/10Animica chain data, free keyless AI inference, quantum randomness, x402 discovery, mining stats.
Fleet Memory
4.7/10Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
Datavidence Financials
4.7/10Normalized US-GAAP financial statements & fundamentals from SEC EDGAR, as MCP tools for LLM agents.
Replication Radar
4.7/10Turn the OpenAIRE Graph into a ranked replication queue with a Science Live verification overlay.
Openlookup
4.7/10OpenLookup: eleven keyless lookups. Model pricing, dep health, stack cost, registries.
M1K3
4.7/10Private memory, documents, voice and a local LLM for your agents, served by a Mac app on-device.
Ddg Agent Services MCP
4.7/10Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.
MCP Server
4.7/10Local memory for AI assistants: remember, recall, forget and expand, stored on your own computer.
Markdown
4.5/10Convert any URL to clean, LLM-ready Markdown
Skillmd Lint
4.5/10Lint a SKILL.md for frontmatter, structure, secrets and size. All 6 tools free.
Openmayhem
4.5/10Use OpenMayhem text, embedding and media models with explicit cost controls.
Scrapiq
4.5/10Any URL to clean text, markdown, or JSON for LLM/RAG pipelines.
Web Scrape
4.5/10Scrape any URL into clean LLM-ready Markdown, or crawl a whole site.
Model Hub
4.5/10Find open models and get download links with the SHA-256 each file must have.
Modelright
4.5/10Live registry of AI model specs, context windows, and per-token pricing.
Citepath
4.5/10Citepath public MCP server for LLM readiness audits and public scan results.
Dossier
4.5/10MCP server for dossier automation standard - enables LLMs to discover, verify, and execute dossiers
Security
4.5/10Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
MCP Server
4.5/10Model intelligence for AI agents — syntax, params, pricing for 67+ generative AI models.
Powerbi Modeling MCP
4.5/10The Power BI Authoring MCP server lets an AI agent create and change Power BI semantic models.
MCP Server
4.5/1063 paid services via USDC: crypto analytics, satellite, IoT, AI inference, prediction markets.
MCP Server
4.5/10File conversion for AI agents: office docs, PDF to Word, video, and LLM-ready markdown via API.
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.