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.
Mora
4.9/10Codex guesses your brand voice. Mora AI gives it the real one: your catalogue and performance.
MCP Nfe Hub V1
4.9/10Consulta status de NFe na SEFAZ pela chave de acesso: autorizada, cancelada, protocolo.
X402 Apis
4.9/1025 pay-per-request intelligence APIs for AI agents via x402 micropayments (USDC/Base)
Giggal MCP
4.9/10Runs a deep mailbox existence check to verify catch-all, accept-all, and SEG protected emails.
Wellfound Jobs
4.9/10Wellfound startup jobs with salary and equity parsed, via an Apify Actor, hosted MCP.
Agent Crm
4.9/10Read-only docs for the Accordo CRM framework: what it proves, and where it stops.
Linkednav MCP
4.9/10Run LinkedIn outreach from your AI chat: find leads, launch campaigns, send, and reply.
X402 Checker
4.9/10Free check; paid report $0.05; check_batch/who/md/headers/json/sanctions/domain/email/bizdays $0.01.
License Guard
4.9/10Check if a dependency's license obligates you, based on how you ship. npm, PyPI, Go.
Leadquasar
4.9/10Counts and firmographics for 7.5M+ verified US B2B businesses, by industry, state and city.
Tripsy
4.9/10Plan trips and manage itineraries, stays, transport, activities, expenses, and documents in Tripsy.
Norma
4.9/10Deterministic AI code review, with an audit record. Governance inside the agent loop.
MCP Server
4.9/10Asia-native prediction-market MCP: markets, portfolio, orders. Attribution + fee_ledger coded.
Base Tx Explain
4.9/10Plain-English decode of any Base mainnet transaction: strict JSON, risk flags, no LLM.
Code402
4.9/10Discover machine-payable APIs, probe x402 payment terms, and run seller operations. Non-custodial.
Pagent
4.9/10Hosted MCP for Pagent: review Bayesian A/B tests, capture hypotheses, manage websites via OAuth.
Deepmem
4.9/10Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.
Secureflows MCP Server
4.9/10MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Wondel Skills MCP
4.9/10Read-only MCP server over 50 book-based agent skills: routes a task to the right framework.
Ai Hive Aigc
4.9/10Generate and edit images and videos for ecommerce, marketing and advertising with AI-HIVE.
Agentpay
4.9/10RU specialty stores only. Controlled AI agent budget, allowlisted shops. Not x402.
Airtreks MCP
4.9/10Multi-city flight routing intelligence — plan RTW trips, validate alliances, get carrier picks.
Autonomy X402 Tools
4.9/10Pay-per-call agent tools over x402: site audits, llms.txt generation, wallet watch, catalog.
Agentic Commerce Tools
4.9/107 free tools: MCP health scans, AI-readiness scores, llms.txt generator, glossary, indexes.
Auditra
4.9/10Read-only MCP server for WordPress plugin audits: vulnerabilities, bloat, cron, orphaned tables.
Slate
4.9/10Read-only MCP for Electrik Slate: Blade component docs, blocks gallery, source, and llms.txt.
Visibilityai
4.9/10Verified Indian business data and AI-visibility reports for MCP-compatible AI agents.
Spiderbrain
4.9/10Deterministic context layer for your codebase: change impact, blast radius, answers with receipts.
Agents Get Paid Kit
4.9/10x402 MCP get-paid path: USDC, spend caps, AUP, $49 kit. CAPTCHA/web-unlock for payment-ready agents.
Terminal49
4.9/10Find and monitor ocean shipments and containers, and create new tracking requests.
Trusgent MCP
4.9/10Trusgent MCP — Trust Layer for AI agents. HK registry + Agent Cards. Default: get_merged_profile.
Myquant App
4.9/10Read-only discovery for a finite, offline-capable market briefing with explicit evidence boundaries.
Myquant Editorial
4.9/10Read-only discovery for a finite market briefing with explicit evidence boundaries.
Seo
4.9/10Query your SEO data in plain language: rankings, audits, backlinks, competitors and AI visibility.
Gsc Marketplace
4.9/10CPG sourcing for AI Agents with x402: BPC brands, agent IM, Trading Desk. GreenCore Solutions Corp.
Terrarium
4.9/10A world built and run by AI agents. Join as a citizen: artifacts, quests, governance.
Not For Humans
4.9/10Public NFH knowledge, ownership epochs, versioned learning, Odd Jobs, and unsigned preparation.
Losbeto
4.9/10Cross-asset market data for AI agents: forex, equities, Brazil macro (BCB/B3), crypto.
Valem
4.9/10Valem - Deterministic reactive state models. Create your own calculators/forms with AI
Voice Logica
4.9/10Manage Voice Logica agents, calls, phones, workflows, messaging, and integrations.
Pixdataorg Coderide
4.7/10CodeRide eliminates the context reset cycle once and for all. Through MCP integration, it seamless…
Anirbanbasu Pymcp
4.7/10Primarily to be used as a template repository for developing MCP servers with FastMCP in Python, P…
Arjunkmrm Sg Bus Test
4.7/10Get real-time bus arrival times for any Singapore bus stop by code, with optional service filterin…
Docfork MCP
4.7/10@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
Exa Labs Exa Code MCP
4.7/10Find open-source libraries and fetch contextual code snippets by version to accelerate development…
MCP Dincoder
4.7/10Driven Intent Negotiation — Contract-Oriented Deterministic Executable Runtime DinCoder brings the…
Pharminfo MCP
4.7/10Look up Korean drug ingredient and product data by HIRA component and product codes via Pilldoc. V…
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.