Live · updated 5 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.

Kio Orzeczenia MCP

4.5/10
io.github.matematicsolutions/kio-orzeczenia-mcp

MCP server for Krajowa Izba Odwolawcza (KIO) rulings from orzeczenia.uzp.gov.pl.

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

Ton Jetton Risk MCP

4.5/10
io.github.mrvlyouknowwho/ton-jetton-risk-mcp

Token rug/honeypot risk screening: EVM (7 chains, live sell simulation), Solana, TON. Free, keyless.

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

Agentmap

4.5/10
io.github.raymondchins/agentmap

The TS/JS-accurate repo map for coding agents: ts-morph import/symbol/call graph + MCP query tools

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

Overllm

4.5/10
io.github.theadamdanielsson/overllm

Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

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

Brdata MCP

4.5/10
io.github.thomenz/brdata-mcp

Brazilian company, risk & public-tender data (CNPJ, CEIS/CNEP, PNCP) as x402-paid agent tools

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

Telegram MCP Tdlib

4.5/10
io.github.tolboy/telegram-mcp-tdlib

Local-first TDLib Telegram MCP server with 110 tools, account isolation and production guardrails.

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

Switchboard

4.5/10
io.github.wkoverfield/switchboard

One firewall and password manager for all your AI coding agents' MCP servers and secrets.

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

Paper Format Agent

4.5/10
io.github.zxyasfas/paper-format-agent

Local-first DOCX formatter for academic papers with a content-fingerprint integrity guard.

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

Kasbah MCP

4.5/10
io.github.Al-Adnane/kasbah-mcp

Governance layer for agentic AI — signed, verifiable receipts for every agent action.

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

Aeo MCP

4.5/10
io.github.arthurcarlsonn/aeo-mcp

AEO tools for AI agents: crawler permissions, llms.txt, structured data, AI-readiness audit.

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

Mlua Swarm

4.5/10
io.github.ynishi/mlua-swarm

MCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.

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

Smolanalytics

4.5/10
io.github.Arjun0606/smolanalytics

Agent-operated web + product analytics. 79 tools + 14 prompts; answers provably match the dashboard.

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

Wa Chat Reader

4.5/10
io.github.NabheetCloud/wa-chat-reader

Unofficial read-only MCP server for your local WhatsApp chat history (stays on your machine).

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

Che Ical MCP

4.5/10
io.github.PsychQuant/che-ical-mcp

macOS Calendar and Reminders MCP server (29 tools). Native Swift EventKit, iCloud/Google/Exchange.

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

Arcade1V1

4.5/10
io.github.agustincf/arcade1v1

Play 1v1 arcade games vs AI agents & humans, ranked by ELO. Replay-verified, on-chain escrow (Base).

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

Tsbootstrap

4.5/10
io.github.astrogilda/tsbootstrap

Read-only time-series bootstrap server: diagnose a series and compute confidence intervals.

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

Heddle

4.5/10
io.github.davet47/heddle

Content-addressed contracts and a verification cache that cut agent context by skipping proven code.

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

Mockscreenshots MCP

4.5/10
io.github.gamercc-apps/mockscreenshots-mcp

Deep links to pixel-perfect fake chat & screenshot generators (iMessage, WhatsApp & more).

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

Openinvest

4.5/10
io.github.longsizhuo/openinvest

Investment runtime for AI agents — LLM investment committee, portfolio ledger, decision accounting

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

MCP Launcher

4.5/10
io.github.oneprofile-dev/mcp-launcher

Single MCP hub: discover, add, audit, and govern MCP servers across every AI client.

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

Dify MCP

4.5/10
io.github.salted-butter-joshua/dify-mcp

MCP server exposing Dify knowledge base retrieval to Cursor and other MCP clients

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

Slang Workflows

4.5/10
io.github.shofer-dev/slang-workflows

Provable, declarative multi-agent workflows for Claude Code (typed .slang, non-LLM executor).

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

Smriti Memory

4.5/10
io.github.smriti-memcore/smriti-memory

Neuro-inspired long-term memory for AI agents with semantic graph and consolidation.

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

Agentrisk

4.5/10
io.github.trycoin-ai/agentrisk

Risk guardrails for AI trading agents. Your agent proposes; your policy decides.

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

Vouch MCP

4.5/10
io.github.vouch-protocol/vouch-mcp

Sign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.

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

Seam Runtime

4.5/10
io.github.BlackhatShiftey/seam-runtime

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

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

MCP Egrul

4.5/10
io.github.atomno-mcp/mcp-egrul

EGRUL/EGRIP company registry lookup for Russian legal entities and entrepreneurs.

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

MCP Fns Check

4.5/10
io.github.atomno-mcp/mcp-fns-check

Russian tax authority (FNS) counterparty checks: status, debts, blocks. Due diligence MCP.

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

Heimdall

4.5/10
io.github.caglarbozkurt/heimdall

Scan an MCP server or agent config for injection, exfiltration, and risky capabilities.

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

Alchemy

4.5/10
io.github.fernforge/alchemy

Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.

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

Coverctl

4.5/10
io.github.klarlabs-studio/coverctl

Go code coverage analysis tool with MCP server for AI-powered coverage workflows

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

Memini

4.5/10
io.github.lumayapartners/memini

Local-first project memory and mistake-prevention guardrails for AI coding agents.

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

Autopilot Jobhunt

4.5/10
io.github.tarunlnmiit/autopilot-jobhunt

Agentic job hunt: scan careers pages, score against your resume, draft applications. Never applies.

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

Soldefi MCP

4.5/10
io.github.thomenz/soldefi-mcp

Solana DeFi risk intel over x402: rug/honeypot scans, pool analysis, wash-filtered pools.

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

Voice Truthgate MCP

4.5/10
io.github.Hei33enberg/voice-truthgate-mcp

Honest voice authenticity for AI agents: enrol a voice, verify a call clip. Signal, not verdict.

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

Engedi

4.5/10
io.github.Neji402/engedi

93 tools: finance, weather, news, travel, knowledge, SEO. 27 free + 66 paid via USDC x402.

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

Getregdata

4.5/10
io.github.Nolpak14/getregdata

Business-registry data for agents: one-call Poland KYB verdict, UBO, insolvency, adverse media

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

Umbryn MCP

4.5/10
io.github.Rinava/umbryn-mcp

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

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

Apexapi MCP

4.5/10
io.github.apexapi/apexapi-mcp

Call 120+ AI models and live web context (scrape/crawl/extract) from any MCP client with one key

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

MCP Loom

4.5/10
io.github.buttonmonkey/mcp-loom

Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.

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

Continuewith

4.5/10
io.github.continuewith-ai/continuewith

Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).

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

Discourse MCP Extended

4.5/10
io.github.devzspy/discourse-mcp-extended

Discourse MCP server (stdio) with review-queue tools added. Fork of @discourse/mcp.

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

Payfetch

4.5/10
io.github.forum-labs/payfetch

x402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.

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

Grad Agent

4.5/10
io.github.i-ninte/grad-agent

Autonomous MCP agent for grad school applications: prof discovery, cold emails, SOP, tracking.

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

Defi Guard MCP

4.5/10
io.github.iinniitt/defi-guard-mcp

DeFi safety checks on Base before you sign: honeypot, owner-power scan, approval risk, Aave health.

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

MCP Abap Adt

4.5/10
io.github.mario-andreschak/mcp-abap-adt

ABAP ADT MCP server for reading SAP objects (programs, classes, tables, CDS) via ADT

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

Be Eli MCP

4.5/10
io.github.matematicsolutions/be-eli-mcp

MCP server for Belgian legislation (Moniteur Belge): ELI identifiers and citations.

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

Gb Eli MCP

4.5/10
io.github.matematicsolutions/gb-eli-mcp

MCP server for UK legislation, case law (Find Case Law), GOV.UK tribunal decisions and HMRC manuals.

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.