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.
Cnnfag
4.5/10CNN's Fear & Greed index for the US stock market: score, rating, indicators and daily history.
Analytixus MCP
4.5/10Analytixus DnAML repository access (read/write nodes, tree navigation, solutions) via MCP.
Evr
4.5/10Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.
Scanpay
4.5/10Code security scanner for AI agents. 45+ vulnerability patterns, AST analysis, Solana micropayments.
Chimeraforge
4.5/10Local-first LLM deployment planner: GPU/VRAM sizing, cost and latency, with provenance
Publiar
4.5/10Ecrit des lead magnets LinkedIn qui refusent d'inventer, rend le visuel et publie.
Chamber
4.5/10Cited Q&A over your own notes, plus drift detection when a cited source changes. Local-first CLI.
Dotplot MCP
4.5/10Product analytics for user flows: aha moments, retention, funnels, per-user dot plots. YC method.
Droidsight
4.5/10Drives a real Android device over ADB and attaches the resulting screen to every action.
MCP Sandbox Computer Vm For Ai
4.5/10Named Docker and Fly Machine sandbox computers with an interactive MCP App dashboard.
Exam Sheet
4.5/10Generate a timed exam on any topic and take it in an interactive exam sheet with live grading.
Halowerk MCP
4.5/10134 paid APIs as MCP tools, billed per call in USDC on Base. No account, no login.
Meet Live Assist
4.5/10Your own agent inside a live Google Meet or Zoom call. Local-first, no hosted service.
Semver Checks
4.5/10Detect breaking changes in your TypeScript library's public API and recommend the SemVer bump.
Shopify Store Builder MCP
4.5/10MCP server for building Shopify stores via the Admin GraphQL API: themes, pages, and navigation
Qseow MCP
4.5/10Agent tools for Qlik Sense Enterprise on Windows: troubleshoot, govern, query and build.
Oraclebone
4.5/10Audited tarot, I Ching, Xiao Liu Ren, Bazi (Four Pillars). Model never invents results.
Sas MCP Server
4.5/10Execute SAS code and query Compute, CAS, and model APIs on SAS Viya via OAuth 2.0.
Google Ads Manager MCP
4.5/10Unofficial MCP server for Google Ads: reporting plus safe draft/confirm campaign management.
Blazingcdn MCP
4.5/10Manage BlazingCDN from AI agents: CDN zones, cache, metrics, domains, cloud storage and video CDN
Mellos Mapping
4.5/10Live layered dependency map for bottom-up development, drawn by the agent in a terminal pane.
Claude Agy MCP
4.5/10Delegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.
Jules Dispatch
4.5/10Batch-dispatch coding tasks to Google Jules: 50 parallel sessions, plan approval, PR collection.
MCP Docs Ask
4.5/10Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Powerbi Pbix MCP
4.5/10Local Power BI authoring for AI agents: edit .pbix, semantic model, report, and Power Query.
Looktwice MCP
4.5/10Email, EU VAT, IBAN, and domain validation plus evidence-backed U.S. CPSC recall screening.
Hlix
4.5/10Work with Hlix projects, tasks, cycles, comments, and verified reviews in one workspace.
Iamf Sentinel MCP
4.5/10MCP server for the iamf-sentinel IAMF conformance validator and the iamf-loom packager
Aiterm MCP
4.5/10Persistent terminals and one launcher for Claude, Codex, Grok, and Cursor harnesses.
Apex Contabil
4.5/10Framework MCP do Apex ERP Contábil: CNAEs, jurídico, obrigações, financeiro, marketing e WhatsApp.
Longhorn MCP
4.5/10MCP server for the Longhorn distributed storage manager API, with a --read-only mode.
Trmm MCP
4.5/10Read your TacticalRMM fleet; run commands only after per-command human approval.
Secretguard MCP
4.5/10Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
Drawarch
4.5/10Create editable Draw.io architecture diagrams from prompts and reference images.
Stateark
4.5/10Local-first version control for AI work. Savepoint and resume your project state across chats.
Sendgrid MCP Secure
4.5/10Security-first SendGrid MCP server: dry-run default, recipient allowlists, rate caps, audit log.
Packkit MCP
4.5/10Scaffold, compose, and upgrade modern multi-language projects as a native tool for AI agents.
Url Manager MCP
4.5/10Agent-first bookmark management with auto-registration, categories, tags, and shared collections.
Ouroboros
4.5/10Pins an acceptance spec; the verify command and expected output never enter the success contract.
Sdcgovernance
4.5/10Governance validation for Semantic Data Charter instances; returns OASIS XACML decisions.
Sdcvalidator
4.5/10SDC4 structural validator with ExceptionalValue recovery; thin wrapper over xmlschema.
Unifi Network MCP
4.5/10Every UniFi Network API operation, plus drift detection, topology, and rule prediction no other
Model Council
4.5/10Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
Crawlbit
4.5/10Four free tools to check if AI engines can find, read and recognise a site. No API key.
Bank Of Canada MCP
4.5/10Bank of Canada economic data: exchange rates, policy rate, CPI, bond yields. No API key.
Gguf MCP
4.5/10Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
Statcan MCP
4.5/10Statistics Canada's 8,200+ data tables: CPI, GDP, labour force, housing. No API key.
Xlsx Audit MCP
4.5/10Audit Excel workbooks: formula dependency tracing, circular references, risk smells. Local only.
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.