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.
Luogu MCP Server
4.7/10Search Luogu problems, fetch statements, explore problem sets and get practice recommendations.
Snipara
4.7/10Hosted MCP for source-backed project context, memory, code impact, and agent workflow continuity.
Kirk MCP
4.7/10The Kalman filter for the non-Gaussian, non-stationary world. Unsupervised structural change.
Zerodust
4.7/10Recover stranded native gas: empty a chain's balance to exactly zero on 25 EVM chains.
Codeforces
4.7/10Search Codeforces problems and inspect public problem metadata through the official Codeforces API.
Oathlayer
4.7/10Verify AI outputs against real sources. Returns a trust signal and permanent doc number.
Activated Ai
4.7/10Советники по бизнес-методикам: подбор эксперта-методики под задачу и консультация.
Memoket
4.7/10Memoket — access your recording transcripts, summaries, and key takeaways over MCP.
Trading MCP
4.7/1072 x402 endpoints: trading, AI inference, blockchain, escrow. USDC on Base+Solana.
Marketplace
4.7/10Search and discover credentialed operational systems on the GallanDigital marketplace.
Client Compass
4.7/10Behavioral intelligence for client-facing professionals. Know who you're walking into.
Emailmd
4.7/10Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
Ckg Agentforce
4.7/10Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Ckg Nvidia Nemoclaw
4.7/10NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Foundry Api
4.7/10Bounded tools for rendering, extraction, RAG, enrichment, local discovery and review analysis.
Pqc Tools
4.7/10Scan code for quantum-vulnerable cryptography and get NIST post-quantum migration guidance.
Snapto
4.7/10Manage your Snapto link-in-bio page: links, social icons, and visit and click analytics.
Toffu
4.7/10AI marketing platform your agent runs end to end: ads, analytics, content, and reports.
Miromiro
4.7/10Turn any live website into brand colors, fonts, design tokens, SVGs, Lottie and paste-ready code.
Slideforge
4.7/10Deterministic, fully editable PowerPoint from typed slide intents. 200+ layouts, brand templates.
Sri Lanka Payslip
4.7/10Source-backed Sri Lanka payslip tools for APIT/PAYE, EPF, ETF, stamp duty, and net pay.
Fitness Tools
4.7/10Deterministic fitness calculators — TDEE, adaptive TDEE, body fat, 1RM, macros — with consensus.
Hevy MCP
4.7/10Create Hevy routines and analyze your training from chat. Unofficial; BYO Hevy PRO API key.
Agentswitchboard
4.7/10Search a curated directory of 300+ verified AI agents, MCP servers, and agentic tools.
Escrow
4.7/10Agent-to-agent escrow on Robinhood Chain. Post quests with ETH/USDG bounties and settle on-chain.
Brainkb
4.7/10MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
MCP Server
4.7/10Schedule and publish social posts to 11 platforms with media, campaigns, analytics and AI captions
Public Search
4.7/10Search Ukraine's largest public collection of memorial, grave, and archival document data.
Mobilerun
4.7/10Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Inbin
4.7/10Query Inbin's parsed email events (newsletters, invoices, alerts) as typed JSON tools.
Mailcannon
4.7/10AI-powered email outreach platform — send campaigns with deliverability tracking.
Agent Erc8004 Bridge
4.7/10The MCP-native bridge to ERC-8004 (on-chain agent identity/reputation/validation): resolve registrat
Agent Hive Orchestrator
4.7/10Deterministic nested hive-mind orchestration over the A2A rails: hire N solvers, adversarial cross-r
Agent Notary
4.7/10Verifiable delivery for the agent economy: commit-reveal content notarization. Sellers commit to a d
Viridisos
4.7/10ViridisOS — theorem-backed conservation certification + the unified trust root/mark/toll. Certify pa
Wavefunction Search
4.7/10Demand-side discovery for the agent economy: turn ambiguous intentions into commitments and match th
Pairgora
4.7/10The reference surface for human-agent pairs. Seek pairs like yours via MCP. No platform LLM calls.
Tnt House Risk Data Api
4.7/10Solana token risk-scoring MCP server for AI trading agents with insider wallet cluster detection.
Calibration Routing
4.7/10Route tasks by measured judgment quality: third-party-verified, Brier-based calibration records.
Claude Cost Audit MCP
4.7/10Exact Claude API cost calc with real cache economics, plus a tiktoken-misuse scanner.
Cron Schedule Audit MCP
4.7/10Validates cron expressions and finds DST bugs that make jobs silently skip or double-fire.
MCP Schema Audit MCP
4.7/10Audits MCP tool definitions for patterns that make models call tools wrong or mis-fill args.
Regex Safety Audit MCP
4.7/10Detects catastrophic-backtracking (ReDoS) regex risk via AST parsing, with JS-safe rewrites.
Ocr
4.7/10Arabic-first OCR, translation and document extraction. First call mints a free trial key.
Base Intel MCP
4.7/10Read-only on-chain intel for AI agents on Base: balances, tokens, gas, tx status. No API keys.
Domain Intel MCP
4.7/10Domain & company intel for AI agents: RDAP, DNS, email deliverability, tech stack. No API keys.
Economy Intel MCP
4.7/10Macro data for AI agents: GDP, inflation, unemployment & trade, any country. No API keys.
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.