Live · updated 15 hr ago 25,524 Servers Scored

The MCP Server Directory

Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.

Servers 25,524
Categories 18
Official Servers 0
Remote-Hosted 14,262

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.

X402 MCP

4.5/10
io.github.x402node/x402-mcp

Hundreds of x402-paid APIs as MCP tools, auto-discovered from Coinbase Bazaar. USDC on Base+Solana.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Copilot MCP

4.5/10
io.github.Apex-Foundation/copilot-mcp

Web3 founder diligence: code audit, jurisdiction, fund matching, portfolio, scoring.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Mailboxvalidator

4.5/10
io.github.MailboxValidator/mcp-mailboxvalidator

Email validation MCP server using the MailboxValidator API. It can validate email addresses.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Interminal

4.5/10
io.github.QiuwenZheng/interminal

Lightweight MCP server providing terminal access (SSH & local shells) for AI assistants.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Trustsource

4.5/10
io.github.SurfEther/trustsource

x402-paid domain verification for AI agents — trustscore, SSL, security headers, robots.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Rust stdio

Cli Market World

4.5/10
io.github.Treevu-ai/cli-market-world

Commerce for AI agents. 44 MCP tools. 380 retailers (336 verified), 21 countries, 4 platforms.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Rust stdio

Fake Star Audit

4.5/10
io.github.ardev-lab/fake-star-audit

Transparent rule-based GitHub fake-star detector — LOW/MEDIUM/HIGH with per-rule evidence.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Star Trajectory

4.5/10
io.github.ardev-lab/star-trajectory

Transparent rule-based GitHub star-trajectory classifier + calibrated 100-star/48h projection

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Frugal

4.5/10
io.github.brainsparker/frugal

The open routing layer for AI tools: tool calls routed per policy, decision on every result.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Foundersignal

4.5/10
io.github.carlosalvite/foundersignal

Find SaaS ideas worth building. Revenue data, growth signals and pain points from 10+ sources.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Avito MCP

4.5/10
io.github.elchin92/avito-mcp

An AI agent that runs your Avito account — 148 tools for chats, listings, promotion, orders.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Server

4.5/10
io.github.mobileproxy/mcp-server

MCP server for mobileproxy.space — manage your mobile proxies from Claude, Cursor, Windsurf.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

No Crd

4.5/10
io.github.nogoo9/no-crd

Dynamic pod spawner & proxy for ephemeral AI agent workspaces on Kubernetes without CRDs

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Nira Repl

4.5/10
io.github.pachote/nira-repl

Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Python stdio

Nira Screen Vision

4.5/10
io.github.pachote/nira-screen-vision

Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Nira Temporal

4.5/10
io.github.pachote/nira-temporal

Time-aware scheduling for Claude — manage tasks, reminders, and recurring schedules

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Kernal MCP

4.5/10
io.github.pintomatic/kernal-mcp

Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Scherlok

4.5/10
io.github.rbmuller/scherlok

Zero-config data-quality monitoring: profile a warehouse, detect anomalies, gate CI.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Vestige

4.5/10
io.github.samvallad33/vestige

Local-first memory for AI agents that reaches backward to find a failure's root cause.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Harmony MCP

4.5/10
io.github.xiaoxuzhu303-prog/harmony-mcp

AI copilot for WeChat Mini Program - compile-fix, size analysis, compliance. 20 tools.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Peak Window

4.5/10
io.github.ByteOverDev/peak-window

Ranks the best weather windows to climb any peak worldwide, on the sharpest regional model.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Hedera MCP

4.5/10
io.github.ExpertVagabond/hedera-mcp

Build-only Hedera (Hashgraph) MCP — 73 tools across all core services plus analytics reads.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Seedweaver MCP

4.5/10
io.github.FixtureForge/seedweaver-mcp

Schema-aware relational test data generator with working foreign keys, for any MCP client.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Korg Ledger

4.5/10
io.github.New1Direction/korg-ledger

Verifiable cognition: prove a session ledger is tamper-evident; audit & import any agent's logs.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Tempera

4.5/10
io.github.anvanster/tempera

Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Alchm Kitchen

4.5/10
io.github.gregcastro23/alchm-kitchen

Live transits, ESMS ingredients, cosmic recipes, synastry & transit×natal overlays by alchm.kitchen

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Calendar

4.5/10
io.github.infoinlet-marketplace/mcp-calendar

Google Calendar for AI agents — list/create/delete events and free-busy via OAuth token.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Clickhouse

4.5/10
io.github.infoinlet-marketplace/mcp-clickhouse

Read-only ClickHouse for AI agents — analytics queries, table inspection, sizes, health.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Fetch

4.5/10
io.github.infoinlet-marketplace/mcp-fetch

SSRF-safe URL fetch for AI agents — clean markdown/text/HTML/JSON, plus guarded REST calls.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Git

4.5/10
io.github.infoinlet-marketplace/mcp-git

Read-only Git inspection for AI agents — log, show, diff, status, blame, grep. No writes.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Image

4.5/10
io.github.infoinlet-marketplace/mcp-image

Image generation & editing for AI agents (Runware) — text-to-image, bg removal, upscale.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Openapi

4.5/10
io.github.infoinlet-marketplace/mcp-openapi

Turn any OpenAPI/Swagger spec into MCP tools — each operation an SSRF-guarded tool.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Social

4.5/10
io.github.infoinlet-marketplace/mcp-social

Multi-platform social posting for AI agents (Postiz) — channels, schedule/publish posts.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Translate

4.5/10
io.github.infoinlet-marketplace/mcp-translate

Translation for AI agents — translate, detect, batch; Japanese keigo registers. OpenRouter.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Workflow

4.5/10
io.github.infoinlet-marketplace/mcp-workflow

Workflow automation for AI agents — browse 125 connectors + 234 templates, run via FluxTurn.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Rust stdio

Spotify MCP

4.5/10
io.github.jamiew/spotify-mcp

MCP server connecting LLMs to Spotify, with smart-batching and large-playlist tools

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

X402 MCP Server

4.5/10
io.github.kten-agent/x402-mcp-server

MCP server for Hermes Asia x402 CN/JP market intelligence via USDC on Base. 8 endpoints.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Server Canary

4.5/10
io.github.mindstone/mcp-server-canary

Mindstone-internal release-pipeline test connector; not for use. Single ping tool; no auth.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Plateau Creative MCP

4.5/10
io.github.pixelx-jp/plateau-creative-mcp

PLATEAU 3D city data as scene-editing and glTF export tools for creative LLM agents.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Ml Lab

4.5/10
io.github.rohithraju-ops/mcp-ml-lab

Run end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna).

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Tempo

4.5/10
io.github.tsutera09/tempo

Founder-vitals connector joining human capacity to business load for solo operators.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code TypeScript stdio

Bounty MCP

4.5/10
io.github.weiseer/bounty-mcp

Live coding-bounty deal-flow from verified-escrow GitHub bounties for AI agents.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Llm Oracle

4.5/10
io.github.weiseer/llm-oracle

Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Play Console MCP

4.5/10
io.github.wiseappsai/play-console-mcp

Manage Google Play Console: releases, listings, monetization, reviews, and Android Vitals.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Sniff

4.5/10
io.github.Aboudjem/sniff

QA + a11y scanner: walks your running app's real user flows and reports what's broken.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Ui Ux Suite

4.5/10
io.github.Aboudjem/ui-ux-suite

UI/UX design-audit MCP server: scores a project on 12 dimensions vs WCAG 2.2 + APCA.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Git Courer

4.5/10
io.github.Alejandro-M-P/git-courer

Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Hatchet MCP

4.5/10
io.github.ElliotPadfield/hatchet-mcp

Observe and operate Hatchet workflows from an AI agent — runs, logs, trigger, cancel, replay.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

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.