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.
Star Trajectory
4.5/10Transparent rule-based GitHub star-trajectory classifier + calibrated 100-star/48h projection
Frugal
4.5/10Cost-optimized MCP server: routes every tool call to the cheapest provider that returns a result.
Foundersignal
4.5/10Find SaaS ideas worth building. Revenue data, growth signals and pain points from 10+ sources.
Avito MCP
4.5/10Avito API MCP for AI agents — 148 tools, safe-by-default, stdio or remote HTTP (OAuth 2.1).
MCP Server
4.5/10MCP server for mobileproxy.space — manage your mobile proxies from Claude, Cursor, Windsurf.
No Crd
4.5/10Dynamic pod spawner & proxy for ephemeral AI agent workspaces on Kubernetes without CRDs
Nira Repl
4.5/10Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands
Nira Screen Vision
4.5/10Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen
Nira Temporal
4.5/10Time-aware scheduling for Claude — manage tasks, reminders, and recurring schedules
Kernal MCP
4.5/10Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
Scherlok
4.5/10Zero-config data-quality monitoring: profile a warehouse, detect anomalies, gate CI.
Vestige
4.5/10Local-first memory for AI agents that reaches backward to find a failure's root cause.
Harmony MCP
4.5/10AI copilot for WeChat Mini Program - compile-fix, size analysis, compliance. 20 tools.
Peak Window
4.5/10Ranks the best weather windows to climb any peak worldwide, on the sharpest regional model.
Hedera MCP
4.5/10Build-only Hedera (Hashgraph) MCP — 73 tools across all core services plus analytics reads.
Seedweaver MCP
4.5/10Schema-aware relational test data generator with working foreign keys, for any MCP client.
Korg Ledger
4.5/10Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.
Tempera
4.5/10Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.
Alchm Kitchen
4.5/10Live transits, ESMS ingredients, cosmic recipes, synastry & transit×natal overlays by alchm.kitchen
MCP Calendar
4.5/10Google Calendar for AI agents — list/create/delete events and free-busy via OAuth token.
MCP Clickhouse
4.5/10Read-only ClickHouse for AI agents — analytics queries, table inspection, sizes, health.
MCP Fetch
4.5/10SSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls.
MCP Git
4.5/10Read-only Git inspection for AI agents — log, show, diff, status, blame, grep. No writes.
MCP Image
4.5/10Image generation & editing for AI agents (Runware) — text-to-image, bg removal, upscale.
MCP Openapi
4.5/10Turn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool.
MCP Social
4.5/10Multi-platform social posting for AI agents (Postiz) — channels, schedule/publish posts.
MCP Translate
4.5/10Translation for AI agents — translate, detect, batch; Japanese keigo registers. OpenRouter.
MCP Workflow
4.5/10Workflow automation for AI agents — browse 125 connectors + 234 templates, run via FluxTurn.
Spotify MCP
4.5/10MCP server connecting LLMs to Spotify, with smart-batching and large-playlist tools
X402 MCP Server
4.5/10MCP server for Hermes Asia x402 CN/JP market intelligence via USDC on Base. 8 endpoints.
MCP Server Canary
4.5/10Mindstone-internal release-pipeline test connector; not for use. Single ping tool; no auth.
Plateau Creative MCP
4.5/10PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.
MCP Ml Lab
4.5/10Run end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna).
Tempo
4.5/10Founder-vitals connector joining human capacity to business load for solo operators.
Bounty MCP
4.5/10Live coding-bounty deal-flow from verified-escrow GitHub bounties for AI agents.
Llm Oracle
4.5/10Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing.
Play Console MCP
4.5/10Manage Google Play Console: releases, listings, monetization, reviews, and Android Vitals.
Sniff
4.5/10QA + a11y scanner: walks your running app's real user flows and reports what's broken.
Ui Ux Suite
4.5/10UI/UX design-audit MCP server: scores a project on 12 dimensions vs WCAG 2.2 + APCA.
Git Courer
4.5/10Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.
Hatchet MCP
4.5/10Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.
Timeweaver MCP
4.5/10Synthetic time-series test data with trend, seasonality, noise, and anomalies, for any MCP client.
Oak Longevity MCP Server
4.5/10Longevity medicine MCP: medication dosing, labs, monitoring, drug interactions & intake screening
Painprep MCP Server
4.5/10Interventional pain medicine MCP: Medicare checklists, CPT/ICD-10, ASRA, prior-auth & appeals
Ai Objective Index
4.5/10Read-only Objective-to-Capability Trust Router for source-traced MCP/API candidates.
Korg Introspect MCP
4.5/10Wrap any korg:introspect@v1-aware binary as a Claude Code tool, honoring declared side-effects.
Korg Recall MCP
4.5/10Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Tradingview MCP Thaqif
4.5/10TradingView Desktop bridge for Pine Script, FCPO futures & Wyckoff multi-timeframe analysis.
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.