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.
Talkform
4.5/10Local Talkform schemas, bundled interview templates, and config validation for AI agents.
MCP Server
4.5/10Dispatch human-execution tasks with proof verification, local checks, and compliance reviews.
Radiochron
4.5/10Local-first Wi-Fi incident diagnostics with native BLE scan, history, and risk evidence.
MCP Server
4.5/10Search TradeSearcher strategies and backtests from Claude Code, Cursor, Codex, and other agents.
MCP X402 Pay
4.5/10MCP server that pays x402-gated HTTP endpoints — fetch, and on a 402 authorize, sign, retry
Images MCP
4.5/10Search and download stock images from Unsplash, Pexels, Pixabay, Freepik, StockVault, and Burst
Hwcontract
4.5/10Judge hardware timing/serial against a contract: pass/marginal/fail (WS2812, DShot, logs)
Argentina MCP
4.5/10MCP server exposing Argentine public jurisdiction/registry data (georef) and datasets.
Bind Alias Plus MCP
4.5/10MCP bridge for BindAliasPlus Minecraft mod: game state, screenshots, aliases, and config editing.
Universal Connector MCP
4.5/10Security-first MCP server that connects any OpenAPI, GraphQL, gRPC or SOAP API to AI agents.
Bailinghub Governance
4.5/10Submit and inspect governed AI business actions through a self-hosted BailingHub control plane.
Enpass MCP
4.5/10MCP server for Enpass vaults: entries, passwords and TOTP/2FA codes, keychain-backed.
Veracrypt MCP
4.5/10MCP server to mount and unmount VeraCrypt containers with secure stdin password handling.
Ship MCP
4.5/10Clean TypeScript starter for MCP servers: zod-validated tools, tests, one-command dev loop.
Ellmos Clatcher MCP
4.5/10Utility MCP server: JSON repair, encoding fixes, conversion, duplicates, batch rename, archives.
Windbg MCP
4.5/10WinDbg/DbgEng over MCP: crash dumps, live user & kernel, driver IOCTLs, and TTD.
Qai Consultant MCP
4.5/10Keyless local MCP server for QA: standards retrieval, effort estimation, doc review, test analysis.
MCP Agentic Server
4.5/10Local coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.
Tacitus MCP Server
4.5/10Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Agent Guard
4.5/10Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
Evalgate
4.5/10Statistical checks an agent runs before trusting an AI eval number (is #1 real, judge bias, more).
Numguard
4.5/10Verify a number before an agent asserts it — evals, backtests (Deflated Sharpe), signed receipts.
Agent Search MCP
4.5/10Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence.
MCP Slim Guard
4.5/1076% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery.
Q402 MCP
4.5/10Q402 - gasless payments, yield, escrow, bridge & NAV triggers on 12 EVM chains. Sandbox-default.
Crashdx
4.5/10Diagnoses Apple .ips crash reports: ranks likely causes with cited evidence, not just a stack trace.
Grounder
4.5/10Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Buyforme MCP
4.5/10BuyForMe: pay any x402 URL (USD or EUR) with ArisPay delegated custody. Alias of payagent-mcp.
Cinch
4.5/10Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.
Ai Agent Firewall
4.5/10Every agent action watched, every money-moving one gated, every verdict independently verifiable.
Agent Observability
4.5/10Trace AI agent execution: every tool call, every error, every dollar. Open source, local-first.
Taste Bank
4.5/10Reusable visual design systems for AI coding agents — browse, fetch, and submit styles via MCP.
Obambu Cpanel MCP
4.5/10MCP server exposing cPanel UAPI (domains, DNS, email, MySQL, files) as tools for AI assistants.
Uniswap Tx Builder MCP
4.5/10Builds and simulates unsigned Uniswap v3 liquidity-position transactions — keyless, never signs.
Tracktag MCP
4.5/10AI music analysis for agents: BPM, key, genres, moods, instruments and 35+ tags per track.
Voltix MCP
4.5/10DeFi intelligence for Claude: whale tracking, alpha signals, yields, token safety. USDC on Base.
Crochet Engine
4.5/10Deterministic photo-to-crochet-chart engine: stitch counts, 5 techniques, yarn estimates.
Baseline MCP
4.5/10Statistically rigorous weather and climate context: forecast plus 35-year historical ranking.
Groupdocs Parser MCP
4.5/10MCP server for GroupDocs.Parser — extract text, images, metadata, tables, barcodes via AI.
Groupdocs Total MCP
4.5/10MCP server for GroupDocs.Total — annotate, sign, convert, watermark, parse, redact documents via AI.
Project Human
4.5/109 humanity skills for AI agents — crisis detection, WCAG 2.2, empathy, cultural sensitivity
Consilium Principis
4.5/10AI advisory board (MCP): quotes verified word-for-word against public-domain texts, fail-closed
Invigil
4.5/10Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents.
Discord MCP
4.5/10MCP server for the Discord REST API: 5 read tools always on, 7 write tools env-gated, default off.
Rag MCP
4.5/10Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
Rails MCP
4.5/10Default-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).
Vllm Ops MCP
4.5/10Read-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.
Agentcents
4.5/10Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.
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.