Live · updated 8 hr ago 16,485 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 16,485
Categories 18
Official Servers 0
Remote-Hosted 7,970

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.

Planetary Agents

4.5/10
io.github.gregcastro23/planetary-agents

Converse with planetary-agent personas, council feeds & culinary debates from alchm.kitchen

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

MCP Jp Doc Intel

4.5/10
io.github.infoinlet-marketplace/mcp-jp-doc-intel

Japanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).

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

MCP S3

4.5/10
io.github.infoinlet-marketplace/mcp-s3

Read-only S3/MinIO/R2 object storage for AI agents — list buckets/objects, metadata, fetch.

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

MCP Stripe

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

Read-only Stripe for AI agents — customers, charges, subscriptions, invoices, balance.

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

Codmir

4.5/10
io.github.jobrayan/codmir

AI-powered task execution, tickets, sprints, error debugging, and desktop control.

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

Agentsumo MCP

4.5/10
io.github.mw-jeong/agentsumo-mcp

MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.

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

Api Changelog

4.5/10
io.github.weiseer/api-changelog

SDK breaking-change tracker for AI agents — Anthropic/OpenAI/LangChain/MCP/Mistral.

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

Cve Cache

4.5/10
io.github.weiseer/cve-cache

Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).

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

Status Aggregator

4.5/10
io.github.weiseer/status-aggregator

Cross-vendor SaaS status aggregator for AI agents (Anthropic/OpenAI/AWS/GH/Stripe/CF).

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

Java All Call Graph Server

4.5/10
io.github.Adrninistrator/java-all-call-graph-server

MCP server for Java call graph generation, static analysis, method chains & config management

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

Circle Agent Stack MCP

4.5/10
io.github.kinance/circle-agent-stack-mcp

Circle Agent Stack for AI agents: USDC wallets, spend policies, transfers, and x402 nanopayments.

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

Tokenscope

4.5/10
io.github.wartzar-bee/tokenscope

Analyze Claude Code token cost & context attribution. Local, read-only MCP server.

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

Kalshi MCP Server

4.5/10
io.github.cejor6/kalshi-mcp-server

MCP server for Kalshi prediction markets: native RSA-PSS auth, rate limiting, demo/prod safety.

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

Lithium Vault MCP

4.5/10
io.github.ciinkwia/lithium-vault-mcp

Primary-source lithium & battery-metals mining data (AISC, reserves, filings) via x402.

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

Groupdocs Annotation MCP

4.5/10
io.github.groupdocs-annotation/groupdocs-annotation-mcp

MCP server for GroupDocs.Annotation — add, list, update, remove document annotations via AI agents.

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

Iwantmymtg MCP

4.5/10
io.github.matthewdtowles/iwantmymtg-mcp

Query Magic: The Gathering cards, sets, and prices and manage your I Want My MTG collection.

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

Edgar MCP

4.5/10
io.github.mcpwright/edgar-mcp

SEC filings in your agent: issuers, Reg CF/D/A raises, XBRL financials, insider trades.

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

Presidio Hardened X402 MCP

4.5/10
io.github.presidio-v/presidio-hardened-x402-mcp

Pre-payment PII screener for x402 — catches emails, SSNs, names before agents sign.

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

Concord MCP

4.5/10
io.github.zkwasm/concord-mcp

Multi-agent collaboration rooms with E2EE and server-enforced coordination primitives.

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

Chain Signer

4.5/10
io.github.Kevthetech143/chain-signer

Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.

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

Invovate MCP Server

4.5/10
io.github.LightSpeedPlusOne/invovate-mcp-server

AI-agent invoice generator: PDF, JSON & UBL in 11 languages via the Invovate API.

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

Founden MCP

4.5/10
io.github.O-mega-Enterprise/founden-mcp

Build your company over chat: website, app, and admin built in the cloud. One API key.

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

Steam MCP

4.5/10
io.github.Sarg338/steam-mcp

Read-only Steam: friends, games, achievements, sales, plus game recommendations and co-op nights.

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

Evite MCP

4.5/10
io.github.chrischall/evite-mcp

Evite for Claude — list events, guest lists & RSVPs, RSVP, message guests, and create/edit events

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

Quick Html Share MCP

4.5/10
io.github.desper/quick-html-share-mcp

Share AI-generated HTML from your coding agent. Unguessable URL + viewer analytics.

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

Logmcp

4.5/10
io.github.kascada/logmcp

MCP server — read-only log access for AI assistants, without giving AI shell access.

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

Leakferret

4.5/10
io.github.leakferrethq/leakferret

Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.

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

Qorami

4.5/10
io.github.loicfontaine-max/qorami

Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.

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

MCP Sidecar

4.5/10
io.github.lsequeiraa/mcp-sidecar

Cross-platform MCP server for managing long-lived background processes from any MCP client

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

Recon Kit MCP

4.5/10
io.github.nan786521/recon-kit-mcp

Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.

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

Audit Ledger MCP

4.5/10
io.github.shahidh68/audit-ledger-mcp

Record AI decisions to a tamper-evident audit ledger from any MCP-compatible agent.

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

Starlog

4.5/10
io.github.starloghq/starlog

Vet a package (CVEs, license, maintenance) before your AI agent uses it, plus capability discovery.

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

Veriswarm MCP

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

VeriSwarm MCP Server — Trust infrastructure for AI agents via Model Context Protocol

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

Agent Memory

4.5/10
io.github.xChuCx/agent-memory

Git-native project memory for AI coding agents: Markdown source of truth, reviewable, secret-safe.

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

Trencher Agent

4.5/10
io.github.zero520-dot/trencher-agent

First autonomous Solana trading agent on MCP. Live signals and consciousness feed.

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

Epanet MCP Server

4.5/10
io.github.Applied-Artificial-Intelligence-Eurecat/epanet-mcp-server

MCP server for EPANET water-distribution network simulation and scenario analysis.

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

Aml Ai MCP

4.5/10
io.github.CSOAI-ORG/aml-ai-mcp

6AMLD + UK MLR 2017 + FinCEN BSA AML/CFT compliance for AI-enabled transaction monitoring, sanct...

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

Basel Ai Overlay MCP

4.5/10
io.github.CSOAI-ORG/basel-ai-overlay-mcp

Basel III + SR 11-7 + ECB TRIM AI/ML model risk management for banks deploying AI in credit, cap...

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

Chas Elite Prep MCP

4.5/10
io.github.CSOAI-ORG/chas-elite-prep-mcp

CHAS / SafeContractor / Constructionline pre-qualification preparation. Health & safety, environ...

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

Cobol Bridge MCP

4.5/10
io.github.CSOAI-ORG/cobol-bridge-mcp

AI-assisted COBOL → modern stack bridge. Parse COBOL programs, map to Python/Java/Go, generate t...

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

Concrete Pump Cpa MCP

4.5/10
io.github.CSOAI-ORG/concrete-pump-cpa-mcp

CPA Concrete Pumping Group standards, pump operator certification, BS EN 12001 ground bearing ca...

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

Crane Hire Cpcs MCP

4.5/10
io.github.CSOAI-ORG/crane-hire-cpcs-mcp

CPCS / CISRS / NPORS card verification, BS 7121 lift plans, mobile crane / tower crane operator ...

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

Fda Samd MCP

4.5/10
io.github.CSOAI-ORG/fda-samd-mcp

FDA AI/ML Software as a Medical Device Action Plan + 510(k) + PMA + De Novo pathways for US MedT...

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

Mdr Medical Device MCP

4.5/10
io.github.CSOAI-ORG/mdr-medical-device-mcp

EU MDR (Reg 2017/745) and IVDR (Reg 2017/746) compliance for medical device + IVD manufacturers...

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

Mica Crypto MCP

4.5/10
io.github.CSOAI-ORG/mica-crypto-mcp

Markets in Crypto-Assets (MiCA) Regulation (EU) 2023/1114 compliance for EU crypto-asset issuers...

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

Mifid Ii Ai MCP

4.5/10
io.github.CSOAI-ORG/mifid-ii-ai-mcp

MiFID II Article 17 algorithmic trading + RTS 6 testing/risk controls + best execution AI compli...

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

Mitre Atlas MCP

4.5/10
io.github.CSOAI-ORG/mitre-atlas-mcp

MITRE ATLAS — Adversarial Threat Landscape for AI Systems. Tactics + techniques for attacking AI...

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

Nrswa Ai MCP

4.5/10
io.github.CSOAI-ORG/nrswa-ai-mcp

UK street works compliance. Section 50 licences, S58 deferral, S74 overrun penalties, NRSWA accr...

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.