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.
Sn MCP Server
4.1/10Multi-instance read-only MCP server for ServiceNow
Bot Factory
4.1/10Provision owner-confirmed isolated Telegram Managed Bot instances.
Korean Vocational Learning Map MCP
4.1/10한국 특성화고 전문교과 2022 개정 교육과정 학습 그래프 MCP 서버 (528과목·성취기준 47,625건, 공식 원문 전량 수록)
Deepseek Visionary
4.1/10DeepSeek web vision model as an MCP server with browser auto-login.
Scripthold
4.1/10Secure encoding-aware local workspace runtime for AI agents
Flatcash MCP
4.1/10AI agent payment rail: earn, pay, trade in 152 currencies. Zero fees.
Memtrust
4.1/10Independent, reproducible benchmark harness for agent-memory backends.
Teamspend
4.1/10Compares AI coding tool spend before and after a migration via MCP tools.
Fetchmcp
4.1/10Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot.
MCP Server Wise
4.1/10Wise (formerly TransferWise) MCP server for Model Context Protocol hosts
Gitcontribute
4.1/10Local-first GitHub contribution research workbench
Mermaid Render MCP
4.1/10Renders Mermaid diagram syntax to PNG or SVG images for LLM clients
Alces MCP
4.1/10Alces for Jira Data Center — MCP server bridging Jira DC/JSM with AI agents
Msforms Api
4.1/10Inspect, validate, upload, and submit Microsoft Forms responses
Ownvoice
4.1/10Wraps the ownvoice CLI as a single generic MCP tool for voice/identity checks.
Podcast Guest Crm
4.1/10Manage podcast guest pipeline, outreach drafts, and analytics via 5 MCP tools.
Swarm Rd Orchestrator
4.1/10Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Swarmmesh
4.1/10Multi-agent context sharing, memory, and status coordination via MCP tools.
Openroad MCP
4.1/10The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
Brave MCP
4.1/10MCP server and CLI for Brave DevTools
Freshbooks MCP
4.1/10FreshBooks invoicing for Claude — invoices, clients, estimates, and payments
MCP Server
4.1/10MCP Server for iceDQ Data Reliability Platform
Ihealed
4.1/10AI-powered guided healing meditations and manifestation scripts.
Postgres
4.1/10PostgreSQL MCP — query databases, inspect schemas, explain queries.
Weather Query
4.1/10Read-only current weather lookup by place name using Open-Meteo.
Wechat Writer MCP
4.1/10面向技术博主的 AI 内容加工流水线 MCP —— 从原始素材到公众号草稿箱
Tailscale Compute
4.1/10Run builds, tests, and benchmarks on your own Tailscale compute node.
Mcpsentinel
4.1/10Precision-first security scanning for Model Context Protocol servers.
Web MCP
4.1/10Provider-fixed web search plus transparent URL, DOI, and document fetching
Chemglyph
4.1/10Publication-quality chemical structure and reaction rendering for AI agents.
Browsermesh
4.1/10Isolated multi-session Chromium runtime for external MCP clients over stdio.
Vibo Memory
4.1/10Memory for AI agents: persistent L1/L2/L3, web-search savings, thread memory.
Footnote
4.1/10Every number in an AI answer traces back to the rows that produced it.
Photo S
4.1/10Batch photo processing: compress, convert, EXIF, rename, dedup, cull, galleries
Housecallpro MCP
4.1/10Read Housecall Pro estimates from the customer link your contractor sent you.
Architecture Pattern MCP
4.1/10MCP server that provides architecture design expertise to AI coding agents
Aigentify
4.1/10Audit and generate agent-native product surfaces
Rule Drift
4.1/10Test whether AI agents retain critical instructions as conversations grow.
Peer Cash
4.1/10MCP server for preparing and tracking Peer Cash Base USDC cash-outs
Localkeep
4.1/10Local chronological memory banks you control; Claude recalls them via MCP.
Osmcp
4.1/10A typed, policy-controlled OS capability layer for AI agents.
Pls Touch Grass
4.1/10An MCP server that knows how long it's been since you touched grass
Human Standards
4.1/10Read-only Human Standards guidance for accessible, usable interface design.
Yaml Workflow
4.1/10Expose declarative YAML-defined workflows as MCP tools over stdio
Webhook MCP Server
4.1/10Capture HTTP, email, and DNS callbacks with webhook.site from MCP clients.
Chrome Devtools MCP
4.1/10MCP server for Chrome DevTools
Pickuppatrol MCP
4.1/10Read and change your children's school dismissal plans in PickUp Patrol
Bamboo MCP
4.1/10Read-only MCP server for self-hosted Atlassian Bamboo CI/CD
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.