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.
Genpark Financial Audit
4.1/10Arithmetic consistency checks for supplied financial statement data.
Genpark Jitter Buffer
4.1/10Packet ordering simulation and inter-arrival jitter telemetry.
Genpark Voice Vad
4.1/10Energy and transcript heuristics for voice turn endpoint detection.
Clawdcursor
4.1/10Safe cross-OS desktop control for any AI agent - the fallback execution layer.
Stepgate
4.1/10Agents can't skip steps: runs gated stepfiles on the client's own model.
Supersaas Slots MCP
4.1/10Find available appointments on public SuperSaaS resource schedules
Glamour
4.1/10Browser-measured visual debugging and verification tools for coding agents.
Dienstanweisung Bewachung Lint
4.1/10Pflichtinhalte nach § 17, 18, 20 BewachV und § 34a Abs. 1a GewO
Weiterbildung Foerderquote Lint
4.1/10Kursseiten gegen § 82 SGB III ab 2024-04-01 prüfen: 16 rules, 2 inputs
Receipts
4.1/10Parse raw receipt lines into itemized totals with tax. All data is local.
Accuracite MCP
4.1/10MCP server exposing AccuraCite's citation verification and finding API as tools
Compliance Checker
4.1/10KVKK/GDPR/CCPA compliance checks for codebases
Dependency Auditor
4.1/10CVE scanning for npm/pip/cargo dependencies via OSV
Dns Intelligence
4.1/10DNS record enumeration, misconfiguration and dangling-subdomain detection
Llm Redteam
4.1/10Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints
Memory Poisoning Scanner
4.1/10Scans agent code for untrusted input poisoning persistent cross-session memory
Model Scanner
4.1/10Scans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks
Prompt Injection Scanner
4.1/10Scans RAG content/scraped pages for indirect prompt injection
Prompt Leak Scanner
4.1/10Catches leaked credentials and PII in outbound LLM prompts
Secret Scanner
4.1/10Scans files for leaked secrets and API keys
Ssl Inspector
4.1/10TLS certificate/cipher/protocol inspection
Tool Poisoning Scanner
4.1/10Scans MCP tool definitions for hidden instructions and confused-deputy sinks
Vulnerability Scanner
4.1/10Triggers GuardBee scans, queries findings, AI-assisted remediation guidance
Phantom MCP Server
4.1/10PHANTOM ID MCP payment server: agent-to-agent USDC payments on Base.
Canonic
4.1/10The Open Context Layer for Data Agents
Netlogger MCP
4.1/10NetLogger MCP server. Nets on the air, live check-ins and who's up, past nets.
Turnback
4.1/10Undo a coding agent turn, including shell commands and untracked files.
Brianbooms MCP
4.1/10Brian Booms x402 product catalog as agent tools. Read-only.
Seristack
4.1/10Run YAML-defined shell command stacks as MCP tools
Umd MCP
4.1/10MCP server exposing University of Maryland data
MCP Server For Oscal
4.1/10AI agent tools for Open Security Controls Assessment Language (OSCAL)
MCP Bruno
4.1/10Python MCP server for running and inspecting Bruno API collections.
Agent Cowork Memory
4.1/10Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
Technical Answer Validator
4.1/10Rubric-based technical answer feedback for AI agents; human review required.
Agentgrasp
4.1/10Yes/no questions about local files, and relevant-file search, with TypeSafe Jev
Jev Decision Gate
4.1/10Local Issue triage with optional Jev judgments and calibrated acceptance gates.
Adguardhome MCP
4.1/10Query your AdGuard Home: status, stats, query log. Endpoints per official docs.
Ashby MCP
4.1/10Keyless MCP server for Ashby job boards: openings, departments, locations.
Checkly MCP
4.1/10Assertion checks for status, headers and content - no API key.
Google Books MCP
4.1/10Query Google Books: volume search and details with covers, pages, categories.
Invoice MCP
4.1/10Generate and send invoices across carriers (UPS, USPS, FedEx, DHL).
Lemonsqueezy MCP
4.1/10Query the Lemon Squeezy API: stores, products, product details.
Linear MCP
4.1/10Query the Linear GraphQL API: viewer, teams, issue search.
Ns MCP
4.1/10NS Dutch Railways API: departures, stations, journeys, disruptions, fares.
Omdb MCP
4.1/10Query the OMDb API: movie/series search and full details with ratings.
Openrouteservice MCP
4.1/10Query OpenRouteService: geocode, reverse geocode, driving directions.
Plain MCP
4.1/10Query the Plain GraphQL API: customers, threads, thread details.
Producthunt MCP
4.1/10Query Product Hunt GraphQL: viewer, latest posts, post details.
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.