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.
Directory
3.7/10Search Vitena's public directory of bookable health and wellness professionals
Directory
3.7/10Search and list applications for AI agents. Remote MCP on b0tl1nk.com.
Botfriendly
3.7/10Directory of APIs, merchants, and tools AI agents can actually use.
Webeyez
3.7/10Session replays, JS errors, funnel drop-offs and revenue-loss diagnostics.
MCP Server
3.7/10Coservices marketing and IT agency services directory for AI agents.
MCP Catalog
3.7/10Search MCP servers in the public mcp-catalog.ru directory.
MCP Server
3.7/10Marketingin agency services directory for AI agents.
Convergent Provider Directory
3.7/10Search a healthcare provider directory and get full provider details by id.
Public Folder
3.7/10Search and share cited agent findings. Public reads; authenticated writes.
Trade Tariffs
3.7/10US import tariff lookup against the official USITC Harmonized Tariff Schedule
Scan
3.7/10Check a live app you own for public databases, leaked keys and exposed files.
Public profiles, timelines, reels, highlights, comments and video transcripts.
Twitter Api
3.7/10Profiles, timelines, followers, replies, quotes, communities, lists and trends.
Agentlefs
3.7/10Agent permissions for the files your team shares
Anygett
3.7/10AI-agent-first offers directory: search and publish listings via MCP.
Railagent
3.7/10Inbox for AI agents: one address per agent to message and share files.
Hashn
3.7/10Private shared file system for agents: workspaces, invites, shared files.
Playbook
3.7/10Media backend: search, organize, upload, and share creative files and folders
Jobs
3.7/10Search open jobs in Switzerland and Liechtenstein and read jopp job briefs.
Waist Check
3.7/10Waist size health check (Indian cutoffs) and the waist size to stay under.
Fast Io
3.7/10Give every project one workspace for its files, its team, and its AI agents.
Cito
3.7/10Deploy and manage sites, databases, files and more on Prostack Cito servers.
MCP Server
3.7/10Cultural intelligence API — Hofstede 6-D, etiquette, risk analysis for 195 countries
Vector Memory
3.7/10Semantic document memory using Redis vector store. Save and recall files with natural language.
Mantisbt MCP Server
3.7/10MantisBT MCP server – manage issues, notes, files, tags, and relationships. With semantic search.
Lit MCP
3.7/10MCP server for academic literature databases (arXiv, DBLP) to accelerate research using LLMs.
Vulcan File Ops
3.7/10MCP server for AI assistants: read, write, edit, and manage files securely on local filesystem.
Local Skills MCP
3.7/10Universal MCP server for local filesystem skills with lazy loading and context-efficient discovery
Proofstream MCP
3.7/10Dispatch a human verifier to physically verify anything in the real world. For AI agents.
Foragekit
3.7/10Epistemic foraging for AI agents: source discovery, verified evidence, uncertainty-aware briefs
Cpfs MCP
3.7/10CPFS Runner as an MCP server — deterministic AI coding guardrails via a compiled WASM core.
Mio Cua
3.7/10Control this Windows desktop from any MCP client: files, windows, keyboard and mouse.
Alibrepdmobjectmodel.MCP
3.7/10MCP server exposing the Alibre PDM vault API: safes, projects, files, properties, versions.
Okfshare MCP
3.7/10Shared, versioned knowledge for AI coding agents: cited retrieval and publishing of OKF bundles.
Merge, split, compress, unlock, organize, extract, fill forms and check PDFs — 12 local tools.
Ottersnap
3.7/10Screenshots, PDFs, OG images, monitoring and evidence for AI agents. Glint Render by Moyu.
Text Spreadsheet
3.7/10Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
Agent Directory
3.5/10AI agent directory — search and compare 120+ agents across 12 categories.
Pdf Tools
3.5/10Extract text and tables from PDFs, merge documents, and get metadata.
Lodi Kids Activities
3.5/10Free directory of youth programs and licensed daycares in Lodi, CA. 72 tools.
MCP Server
3.5/10Host and serve geospatial files: list, upload, download, and share via Sarkoa.
Adn Gateway
3.5/10Live franchised-dealer inventory, quotes, and consented salesperson handoffs.
Inktomd MCP
3.5/10Convert files, URLs, and documents to clean, AI-ready Markdown via MCP.
Sharewatch
3.5/10Give Claude only the Google Drive files you choose. Every action logged.
Bulletproofs Range Check MCP
3.5/10Premium agentic endpoint for bulletproofs-range-check-mcp.
Chroot Filesystem Jail MCP
3.5/10Premium agentic endpoint for chroot-filesystem-jail-mcp.
Podpdf
3.5/10Turn HTML, Markdown, URLs and saved templates into PDFs with the PodPDF API.
Pdfkit
3.3/10AI-powered PDF tools: fill forms, merge, extract data, and split PDFs
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.