Live · updated 10 hr ago 9,792 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 9,792
Categories 18
Official Servers 0
Remote-Hosted 3,995

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.

Promptguardscan MCP

4.1/10
space.promptguardscan/promptguardscan-mcp

Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.

4.5Reliab.
7.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Quantifyme

4.1/10
ai.quantifyme/quantifyme

Describe a trading strategy in plain English and deploy a live signal model in one call. No signup.

4.5Reliab.
7.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Nuget

4.1/10
com.microsoft/nuget

A Model Context Protocol (MCP) server for NuGet.

6.5Reliab.
5.0Docs
3.5Maint.
1.0Adopt.
AI / ML stdio

MCP Server

4.1/10
com.picaos/mcp

A Model Context Protocol Server for Pica

6.5Reliab.
5.0Docs
3.5Maint.
1.0Adopt.
AI / ML stdio

MCP Server

4.1/10
com.gammainfra/mcp-server

Smart LLM routing across every major provider via one OpenAI-shape API.

6.5Reliab.
5.0Docs
3.5Maint.
1.0Adopt.
AI / ML stdio

Langfuse

4.1/10
com.pulsemcp/langfuse

MCP server for Langfuse LLM observability — trace and observation analysis.

6.5Reliab.
5.0Docs
3.5Maint.
1.0Adopt.
AI / ML stdio

Professionalwiki Mediawiki MCP Server

3.9/10
ai.smithery/ProfessionalWiki-mediawiki-mcp-server

Enable Large Language Model clients to interact seamlessly with any MediaWiki wiki. Perform action…

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Brandonbosco Sigao Scf MCP

3.9/10
ai.smithery/brandonbosco-sigao-scf-mcp

Provides access to Civic Plus - See Click Fix, allowing you to interact with your data via an LLM.…

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Anotherai

3.9/10
dev.anotherai/anotherai

MCP server for building and testing AI agents with multi-model experimentation and insights.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Apollo Salesforce Mapper

3.9/10
dev.workers.selbyventurecap.cf-worker/apollo-salesforce-mapper

Apollo->Salesforce Lead mapper. No LLM. Strict-fail required fields. PASS/REPAIR/FAIL verdict.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Geo

3.9/10
io.studiomeyer/geo

AI visibility monitoring. 24 tools, 8 LLM platforms, Hallucination Guard. Free tier.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Navisworks MCP

3.9/10
io.scanbimlabs/navisworks-mcp

Navisworks coordination and clash detection via APS — reports, viewpoints, model objects.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

MCP Server

3.9/10
ac.inference.sh/mcp

Run 150+ AI apps — image, video, audio, LLMs, 3D and more. Browse, execute, stream results.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

MCP Server

3.9/10
com.googleapis.compute/mcp

Provides capabilities that let LLM agents perform a range of infrastructure management tasks.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

MCP Server

3.9/10
ai.dragoneye/mcp

Build zero-shot video models for object detection, and category and attribute classification.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Cannon Studio

3.9/10
app.cannonstudio/cannon-studio

Public Cannon Studio MCP for product, pricing, workflow, model, and API answers.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Pimea

3.9/10
ai.pimea/pimea

The hidden intelligence for AI marketing agents. Real campaign data, not LLM guesses.

4.5Reliab.
6.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Nces Education

3.7/10
com.olyport/nces-education

School enrollment, graduation rates, demographics, finance, and Title I data

4.5Reliab.
5.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Investigation Game

3.7/10
tech.skybridge.investigation-game/Investigation-Game

Find out who killed Claude by interrogating the LLM driven suspects...

4.5Reliab.
5.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Time S Up

3.7/10
tech.skybridge.times-up/Time-s-Up

Skybridge Example App showcasing a Time's up game with the LLM

4.5Reliab.
5.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Hf MCP Server

3.5/10
co.huggingface/hf-mcp-server

Connect to Hugging Face Hub and thousands of Gradio AI Applications

4.5Reliab.
4.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

MCP Server

3.5/10
com.tip4serv/mcp-server

Monetize and manage your Tip4Serv store directly from your LLM.

4.5Reliab.
4.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

MCP Server

3.5/10
com.lenderprice/mcp

MCP server that exposes the Lenderprice platform's capabilities to AI models.

4.5Reliab.
4.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

Doing

3.5/10
live.alpic.doing-v2-d5286fe8/doing

simple task manager for your LLM

4.5Reliab.
4.0Docs
3.5Maint.
2.0Adopt.
AI / ML streamable-http Remote

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.