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.
Global Sentinel MCP
4.1/10Polymarket, GDELT, OpenSky, Cloudflare Radar unified as one MCP server.
Waggle MCP
4.1/10Persistent graph-backed conversational memory for AI agents.
MCP Gdbserver
4.1/10MCP server for remote debugging with gdbserver
Qtm4J
4.1/10MCP server for QMetry Test Management for Jira (QTM4J) Open API.
Excel Webview2 MCP
4.1/10MCP server for Excel add-ins via WebView2 CDP
MCP Canary
4.1/10Neo4j MCP Canary — The canary goes first so the rest of us know what's coming
Pyobfus MCP
4.1/10MCP tools for pyobfus — the Python obfuscator for AI-assisted development.
Dep Diff MCP
4.1/10Translates a lockfile diff into a human-readable upgrade plan for npm and PyPI.
Haiku MCP Server
4.1/10DeFi execution for AI agents — swap, lend, bridge, and yield across 22 chains.
Suprsonic MCP
4.1/10One API key, dozens of capabilities for your AI agent. Zero provider auth.
Agent Tasker MCP
4.1/10Minimal stdio MCP server for parallel task execution by AI agents.
Model Council MCP Server
4.1/10Three-model MCP server returning Grok, Gemini, and DeepSeek outputs for Claude.
Perplexity Polza MCP Server
4.1/10Perplexity MCP server backed by the Polza.ai chat completions API.
Seedance Polza MCP Server
4.1/10Seedance video generation MCP server for Polza.ai.
Minuet MCP
4.1/10MCP server exposing Minuet's ERC-8004 agent relationship graph.
Autodesk Revit MCP Server
4.1/10MCP server connecting AI assistants to Autodesk Revit through a local bridge.
MCP Rpcbind
4.1/10MCP server exposing rpcbind/RPC portmapper functionality
Send WhatsApp messages from Cursor, Claude Code, and Codex via MCP.
Agent Guard
4.1/10Constitutional guardrails and loop detection for AI agents
Agent Security
4.1/10Security scanning and threat detection for AI agents
Agentic Observability
4.1/10Agent tracing, cost tracking, anomaly detection for LLM agents
Compliance Shield
4.1/10ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents
Domain Expertise
4.1/10Inject deep domain knowledge into any AI agent
Gcc Intelligence
4.1/10GCC regulatory intelligence, ZATCA e-invoicing, and Arabic NLP for AI agents
Qc Validator
4.1/10Output quality control and validation for AI agents
Scope Guard
4.1/10Hard scope boundaries to prevent AI agent drift
Token Lens
4.1/10Context window token analysis and budget management
T32 Lsp MCP Server
4.1/10TRACE32 CMM LSP via MCP — parse, diagnostics, completions, hover, symbols
T32 MCP Server
4.1/10TRACE32 debugger MCP — session, dialog, field, history, resource inspection
Seojeom MCP
4.1/10Local-first MCP server for Claude/Codex project wiki and graph workflows
Blackhawk MCP
4.1/10BlackHawkMCP - connect AI to Google Sheets
Proxyclaw
4.1/10Residential proxy MCP server. 175M+ IPs in 195+ countries with anti-bot bypass.
Realssh MCP
4.1/10MCP server for SSH remote command execution
Stackguide MCP
4.1/10Dynamic context loading for AI assistants with TDD workflow and AST analysis
A2A Bridge
4.1/10Agent-to-agent communication bridge for multi-agent systems
Agent Costcenter
4.1/10Multi-agent billing and cost allocation tracking
Agent Replay
4.1/10Record and replay AI agent execution for debugging
Docx Forge
4.1/10Professional document generation from structured data
MCP Registry
4.1/10MCP server discovery, indexing, and registration
Secure Vault
4.1/10Encrypted secrets and credential management for agents
Trace Forge
4.1/10Structured execution trace and span logging for AI agents
Mythos Agent
4.1/10Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.
Imagine MCP
4.1/10MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)
Promptlint MCP
4.1/10Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.
Ozon Seller
4.1/10MCP server for Ozon Seller API — products, FBS/FBO, finance, analytics, returns
Semamerge
4.1/10Detects semantic merge conflicts between Git branches using AST-level analysis
Routing Director MCP Server
4.1/10MCP server to integrate with Juniper Routing Director
Safeagent
4.1/10Execution guard for AI agents — prevents duplicate tool calls on retry.
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.