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.
MCP Tool Factory
4.1/10Generate MCP servers from natural language, OpenAPI specs, or database schemas.
Dejared
4.1/10Explore, analyze, and decompile Java JAR files via MCP
MCP Nfse Nacional
4.1/10MCP Server para consulta de NFSe no portal nacional (nfse.gov.br)
Latex MCP
4.1/10Enable AI agents to compile TeX files with LaTeX inside a Docker container.
Glp1Search
4.1/10GLP-1 provider directory, peptide database, and medication comparison tools.
Otp Ojp
4.1/10Validate, introspect, and parse talent profiles (OTP) and job postings (OJP)
Gravity Swarm
4.1/10Agent reputation network — compute tasks, submit proofs, earn ELO via Nostr MCP
MCP Pfsense
4.1/10Manage pfSense firewalls through AI assistants — rules, DHCP, DNS, and more
Agent Skill Loader
4.1/10Dynamically load Claude Code skills into AI agents without copying files.
MCP Server Filesystem
4.1/10MCP server for filesystem access
MCP Stl
4.1/10MCP server for editing STL 3D model files
Envibe
4.1/10Secure permission layer between AI agents and your .env files
Pdfspark MCP
4.1/10Convert HTML or URLs to PDF documents powered by Playwright
Filekiwi MCP Server
4.1/10Upload files to file.kiwi and get shareable links instantly.
Npm Run MCP Server
4.1/10An MCP server that exposes package.json scripts as tools for agents.
Endnote MCP
4.1/10Search, cite, and read PDFs from your EndNote library in Claude Desktop
Darshan MCP
4.1/10Darshan I/O profiler MCP server for analyzing I/O trace files
Parquet MCP
4.1/10MCP server for Apache Parquet files
Journald MCP Server
4.1/10Incident forensic with log files analyzing
Expense MCP
4.1/10Personal Expense Tracker MCP Server — expenses, income, budgets & savings goals
Signforge
4.1/10Send documents for e-signature from AI agents. Upload, sign, and download PDFs.
Ofs MCP
4.1/10NOAA OFS regional ocean model forecasts — water level, temperature, salinity
Stofs MCP
4.1/10NOAA STOFS storm surge forecasts, observation validation, and OPeNDAP data
MCP Server
4.1/10GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations
Ai Context Kit
4.1/10Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
Lu MCP Server
4.1/10Verify AI agent communication with session types and formal proofs
Env Forge MCP
4.1/10Parse, validate, and manage .env environment files
Readme Forge MCP
4.1/10Generate professional README.md files from project analysis
Scrapebadger
4.1/10Twitter/X scraping API for AI agents. Get profiles, tweets, trends, and more.
Basis MCP
4.1/10Stablecoin risk scores, wallet risk profiles, and transaction risk assessment.
Mindbox MCP
4.1/10MCP server for Mindbox CDP API — customer profiles, orders, segments. 3 tools.
Vtimestamp
4.1/10MCP server for verifying and querying vtimestamp proofs on the Verus blockchain
Cvinbio
4.1/10Search professional profiles from the CVin.Bio talent database.
Rulemorph MCP
4.1/10MCP server for CSV/JSON data transformation using YAML rules
Transform Rules MCP
4.1/10MCP server for CSV/JSON data transformation using YAML rules
MCP Upload
4.1/10Public file storage for AI agents. Upload files and get a permalink back.
Proflulab Documentassistant
3.9/10Convert files between formats without quality loss. Speed up your workflow with fast, reliable con…
Pagecrawl MCP
3.9/10Monitor web pages for changes with AI-powered change detection, diffs, and alerts.
Wistia Api MCP
3.9/10Manage Wistia videos, channels, folders, captions, customizations, and analytics via MCP.
Linkmcp
3.9/10Hosted MCP server for LinkedIn. 25 tools for profiles, messages, search, and more.
Commerce Intelligence
3.9/10Commerce intelligence for AI agents. Diagnose drop-offs, fix checkouts, optimize pricing.
Uldl
3.9/10Persistent file storage for AI agents via MCP and curl. Upload, download, and version files.
Api Server
3.9/10Global labour & market data for skills, workforce, planning, stakeholders, jobs, news & profiles
Filesystem MCP
3.9/10Read, create, and edit files.
MCP Drive
3.9/10Google Drive integration with file operations, folder navigation, search, and sharing
MCP Server
3.7/10Quantum computing jobs, arXiv papers & researcher profiles from qubitsok.com
Signal Api
3.7/10Bitcoin 15-min prediction signals with on-chain commitment proofs. L402-gated.
MCP Server
3.7/10Cultural intelligence API — Hofstede 6-D, etiquette, risk analysis for 195 countries
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.