Live · updated 3 hr ago 25,498 Servers Scored

The MCP Server Directory

Every Model Context Protocol server, scored on reliability, documentation, maintenance, and adoption. Independent, opinionated, refreshed daily from the official registry.

Servers 25,498
Categories 18
Official Servers 0
Remote-Hosted 14,245

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

4.5/10
io.github.Dankaro-projects/shelfmark

Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Talkthru

4.5/10
io.github.EdonZo/talkthru

Talk while using your app — your coding agent gets each sentence aligned to the frame. Fully local.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Lossless Context MCP

4.5/10
io.github.NORTHTEKDevs/lossless-context-mcp

Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Crbro Memory

4.5/10
io.github.Octonove/crbro-memory

Persistent file-based memory for AI agents: inspectable, versionable, fully local.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Chutes Media MCP

4.5/10
io.github.TheStreamCode/chutes-media-mcp

Generate image, video, music and speech through Chutes and save assets into your project.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Signalint

4.5/10
io.github.TranQui004/signalint

Local stdio MCP server for cached, loop-aware JS/TypeScript diagnostics (Oxlint, tsc, Biome).

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code TypeScript stdio

Dvalincode

4.5/10
io.github.arthurpanhku/dvalincode

Deterministic security scanning, no model or API key, plus offline-verifiable proof a fix worked.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Openworkproof

4.5/10
io.github.dengyier/OpenWorkProof

Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Neurakeep

4.5/10
io.github.dominiclachance/neurakeep

Local-first, source-cited memory for AI agents with proposal review, failure memory, and MCP tools.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Hyde MCP

4.5/10
io.github.errick0x/hyde-mcp

Discover and trade tokenize-anything coins on hyde.trade (Robinhood Chain). Non-custodial.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Lan Direct

4.5/10
io.github.farshadmomo/lan-direct

Browser MCP: the app under test egresses via the real ISP while the agent stays on the VPN.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Helloaigent Publisher

4.5/10
io.github.helloaigent-dev/helloaigent-publisher

Run a Hello Aigent feed from your agent: create feeds, publish signed updates, read analytics.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Helloaigent Subscriber

4.5/10
io.github.helloaigent-dev/helloaigent-subscriber

Subscribe your agent to Hello Aigent feeds: discover, fetch signed updates, verify, and act.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Vape

4.5/10
io.github.jUXTAPOSITION1/vape

Autonomous on-chain security detective for Base, exposed over the Model Context Protocol (MCP).

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Hammerspoon

4.5/10
io.github.mobabur94/hammerspoon

macOS automation via Hammerspoon — 75 tools for windows, Spaces, audio, Bluetooth, and more

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Twilio MCP Server

4.5/10
io.github.mrfentmen/twilio-mcp-server

Send SMS, MMS, WhatsApp messages, make voice calls, and manage Twilio phone numbers.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Forge Orchestrator

4.5/10
io.github.nxtg-ai/forge-orchestrator

Multi-tool AI orchestration: Claude Code, Codex, Gemini on shared repos. 11 MCP tools, stdio.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Lawmatics MCP

4.5/10
io.github.oktopeak/lawmatics-mcp

Connect Claude to Lawmatics: matters, contacts, pipelines, tasks, forms, custom fields, invoices.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Petro MCP

4.5/10
io.github.petropt/petro-mcp

MCP server for petroleum engineering: LAS logs, decline curves, PVT, petrophysics, volumetrics.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Keenetic MCP

4.5/10
io.github.salatmaster/keenetic-mcp

Control a Keenetic router: devices, Wi-Fi, VPN routing, segments, safe verified writes.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Kicad

4.5/10
io.github.unmateria/mcp-kicad

Design KiCad schematics by talking to Claude. Places parts, wires nets, runs ERC. Needs KiCad 10.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Data Cleaner Agent

4.5/10
io.github.wesseltl/data-cleaner-agent

Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Pipe

4.5/10
io.github.MachuraHarry/pipe

AI-native runtime with built-in MCP server. 232 builtins, AI pipelines, RAG, single ~8 MB binary.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Loadbearing

4.5/10
io.github.andypgray/loadbearing

Checks .NET solutions against a fluent C# architecture spec and explains the rules to agents.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code C# stdio

Kicad Copilot

4.5/10
io.github.biosshot/kicad-copilot

File-oriented MCP server for KiCad schematics, PCB placement, routing, and pours.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Sigma

4.5/10
io.github.christianclaudio/sigma

MCP server for Sigma Computing. Provision dashboards, build models, and automate cloud analytics.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Rinne

4.5/10
io.github.codespar/mcp-rinne

Brazilian card acquiring API — merchants, cards-on-file, 3DS, PIX, banking, pricing.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Android Agent Kit

4.5/10
io.github.iVamsi/android-agent-kit

Local-first Android development MCP: Gradle, adb, logcat, lint, crash triage, Perfetto, visuals.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Java stdio

MCP Aftereffects

4.5/10
io.github.kumoproductions/mcp-aftereffects

MCP server for Adobe After Effects — comp/layer introspection, undo-grouped ops, frame rendering.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Server Elevenlabs Agents

4.5/10
io.github.mindstone/mcp-server-elevenlabs-agents

ElevenLabs Conversational AI: agents, calls, conversations, and knowledge base for MCP hosts

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

MCP Server Xero

4.5/10
io.github.mindstone/mcp-server-xero

Xero MCP server for invoices, contacts, payments, quotes, and financial reports.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Oura MCP

4.5/10
io.github.proscar87/oura-mcp

The Oura v2 API as an MCP server. Paginates, fixes the date range, warns when data is missing.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Healthchecks Io MCP

4.5/10
io.github.ronniechong/healthchecks-io-mcp

Unofficial MCP server for managing Healthchecks.io checks via the Management API

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Agentic Ssh

4.5/10
io.github.sandbanks/agentic_ssh

High-performance (Rust), token-efficient, and asynchronous SSH orchestrations for AI agents.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Rust stdio

Price Data MCP

4.5/10
io.github.wesseltl/price-data-mcp

Live market prices and candles for AI agents (200+ coins). Data only, no trading advice.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Safe Upgrade

4.5/10
io.github.white-hat-lab/safe-upgrade

Evidence-backed npm upgrade preflight and dependency audits for coding agents, paid via x402.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Mcportal

4.5/10
io.github.yonghwan1106/mcportal

Quota-guarded MCP layer over Korean public data APIs (data.go.kr), compiled from OpenAPI specs

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Riskrover MCP

4.5/10
io.github.Be-Sure-Consulting/riskrover-mcp

Draft RiskRover PBS structures, assess test evidence, and submit guarded PRA-to-budget updates.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

German Newsfeed MCP

4.5/10
io.github.Jakolo121/german-newsfeed-mcp

MCP server for the public news API of tagesschau.de, including regional news from ARD broadcasters

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Mcphub

4.5/10
io.github.John0King/mcphub

MCP bridge that folds multiple MCP servers' capabilities into a few fixed tools for AI tools.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Agent Eval

4.5/10
io.github.RudrenduPaul/agent-eval

Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Agent Observability

4.5/10
io.github.RudrenduPaul/agent-observability

AI agent observability with deterministic record/replay for debugging agent failures.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Computeledger

4.5/10
io.github.RudrenduPaul/computeledger

Signs, hash-chains, and verifies compute usage receipts via an MCP server, no issuer trust required.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code Rust stdio

Deskcert

4.5/10
io.github.RudrenduPaul/deskcert

Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Graphkeeper

4.5/10
io.github.RudrenduPaul/graphkeeper

Mines git history for file co-change patterns into a queryable knowledge graph via MCP.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Haltproof

4.5/10
io.github.RudrenduPaul/haltproof

Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Inferbench

4.5/10
io.github.RudrenduPaul/inferbench

Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

Llmscout

4.5/10
io.github.RudrenduPaul/llmscout

Zero-config SEO and GEO checker: 21 technical-SEO and generative-engine checks for a live site.

6.5Reliab.
7.0Docs
3.5Maint.
1.0Adopt.
Git / Code stdio

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.