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.
Shelfmark
4.5/10Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.
Talkthru
4.5/10Talk while using your app — your coding agent gets each sentence aligned to the frame. Fully local.
Lossless Context MCP
4.5/10Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.
Crbro Memory
4.5/10Persistent file-based memory for AI agents: inspectable, versionable, fully local.
Chutes Media MCP
4.5/10Generate image, video, music and speech through Chutes and save assets into your project.
Signalint
4.5/10Local stdio MCP server for cached, loop-aware JS/TypeScript diagnostics (Oxlint, tsc, Biome).
Dvalincode
4.5/10Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.
Openworkproof
4.5/10Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Neurakeep
4.5/10Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.
Hyde MCP
4.5/10Discover and trade tokenize-anything coins on hyde.trade (Robinhood Chain). Non-custodial.
Lan Direct
4.5/10Browser MCP: the app under test egresses via the real ISP while the agent stays on the VPN.
Helloaigent Publisher
4.5/10Run a Hello Aigent feed from your agent: create feeds, publish signed updates, read analytics.
Helloaigent Subscriber
4.5/10Subscribe your agent to Hello Aigent feeds: discover, fetch signed updates, verify, and act.
Vape
4.5/10Autonomous on-chain security detective for Base, exposed over the Model Context Protocol (MCP).
Hammerspoon
4.5/10macOS automation via Hammerspoon — 75 tools for windows, Spaces, audio, Bluetooth, and more
Twilio MCP Server
4.5/10Send SMS, MMS, WhatsApp messages, make voice calls, and manage Twilio phone numbers.
Forge Orchestrator
4.5/10Multi-tool AI orchestration: Claude Code, Codex, Gemini on shared repos. 11 MCP tools, stdio.
Lawmatics MCP
4.5/10Connect Claude to Lawmatics: matters, contacts, pipelines, tasks, forms, custom fields, invoices.
Petro MCP
4.5/10MCP server for petroleum engineering: LAS logs, decline curves, PVT, petrophysics, volumetrics.
Keenetic MCP
4.5/10Control a Keenetic router: devices, Wi-Fi, VPN routing, segments, safe verified writes.
MCP Kicad
4.5/10Design KiCad schematics by talking to Claude. Places parts, wires nets, runs ERC. Needs KiCad 10.
Data Cleaner Agent
4.5/10Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.
Pipe
4.5/10AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.
Loadbearing
4.5/10Checks .NET solutions against a fluent C# architecture spec and explains the rules to agents.
Kicad Copilot
4.5/10File-oriented MCP server for KiCad schematics, PCB placement, routing, and pours.
Sigma
4.5/10MCP server for Sigma Computing. Provision dashboards, build models, and automate cloud analytics.
MCP Rinne
4.5/10Brazilian card acquiring API — merchants, cards-on-file, 3DS, PIX, banking, pricing.
Android Agent Kit
4.5/10Local-first Android development MCP: Gradle, adb, logcat, lint, crash triage, Perfetto, visuals.
MCP Aftereffects
4.5/10MCP server for Adobe After Effects — comp/layer introspection, undo-grouped ops, frame rendering.
MCP Server Elevenlabs Agents
4.5/10ElevenLabs Conversational AI: agents, calls, conversations, and knowledge base for MCP hosts
MCP Server Xero
4.5/10Xero MCP server for invoices, contacts, payments, quotes, and financial reports.
Oura MCP
4.5/10The Oura v2 API as an MCP server. Paginates, fixes the date range, warns when data is missing.
Healthchecks Io MCP
4.5/10Unofficial MCP server for managing Healthchecks.io checks via the Management API
Agentic Ssh
4.5/10High-performance (Rust), token-efficient, and asynchronous SSH orchestrations for AI agents.
Price Data MCP
4.5/10Live market prices and candles for AI agents (200+ coins). Data only, no trading advice.
Safe Upgrade
4.5/10Evidence-backed npm upgrade preflight and dependency audits for coding agents, paid via x402.
Mcportal
4.5/10Quota-guarded MCP layer over Korean public data APIs (data.go.kr), compiled from OpenAPI specs
Riskrover MCP
4.5/10Draft RiskRover PBS structures, assess test evidence, and submit guarded PRA-to-budget updates.
German Newsfeed MCP
4.5/10MCP server for the public news API of tagesschau.de, including regional news from ARD broadcasters
Mcphub
4.5/10MCP bridge that folds multiple MCP servers' capabilities into a few fixed tools for AI tools.
Agent Eval
4.5/10Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Agent Observability
4.5/10AI agent observability with deterministic record/replay for debugging agent failures.
Computeledger
4.5/10Signs, hash-chains, and verifies compute usage receipts via an MCP server, no issuer trust required.
Deskcert
4.5/10Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
Graphkeeper
4.5/10Mines git history for file co-change patterns into a queryable knowledge graph via MCP.
Haltproof
4.5/10Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
Inferbench
4.5/10Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Llmscout
4.5/10Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site.
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.