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.
Neuronscope
4.5/10Traces which neurons and attention heads drive a language model's output via MCP tools.
Releaseguard
4.5/10Scans datasets/models for PII/secrets, redacts, and packages a public-release bundle via MCP.
Tenantguard
4.5/10Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.
Tokentrust
4.5/10Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Workloadtruth
4.5/10Classifies GPU workloads as inference or training from telemetry alone via MCP tools.
Regon MCP
4.5/10Look up Polish businesses in the GUS REGON register (BIR1) by NIP, REGON, or KRS.
Ms 365 MCP Server
4.5/10Interact with Microsoft 365 and Office services through the Microsoft Graph API.
Docsift
4.5/10Convert a document once, then get back only the passages that answer a question.
Angi MCP
4.5/10Angi for Claude — find home-service pros by trade and city, read ratings and reviews
Google Data MCP
4.5/10Google Trends, YouTube, Ads Transparency and Play reviews over plain HTTP. No API key.
Getdigitalcraft MCP Render
4.5/10Deterministic image rendering with exact typography. Pay per call in USDC, no account.
MCP Server
4.5/10Attach weapons and props to rigged 3D characters: hand-bone detection, fist close, engine binds.
Procheiron
4.5/10Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.
Strimzi Kafka Cli
4.5/10Manage Apache Kafka on Kubernetes via Strimzi. Clusters, topics, users, connectors, MM2.
Fundlens
4.5/10SEC fund holdings for AI agents: who holds X, what changed, returns, flows, and fund overlap.
Xaf Logic Explainer
4.5/10Query your DevExpress XAF app: entities, controllers, actions, rules, Model Editor.
Agentic Wallet Guardian V3
4.5/10Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
Agent Toolkit
4.5/10Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.
King Crimson MCP
4.5/10King Crimson discography and live-performance history with a curated line-up-era model.
Rules MCP
4.5/10MCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity.
Elementor Ultra MCP
4.5/10Build Elementor sites with AI agents - native, editable pages via ~90 MCP tools. Free & MIT.
Agenticworkspace
4.5/10Wraps the AgenticWorkspace CLI as a single generic MCP tool for repo workspace scans.
Continuityguard
4.5/10Wraps the ContinuityGuard CLI as a single generic MCP tool for video-clip continuity scans.
Evolveguard
4.5/10Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.
Freelancer Payment Protection
4.5/10Wraps the fpp CLI as a single generic MCP tool for freelancer client payment-risk checks.
Masterytrace
4.5/10Wraps the MasteryTrace CLI as a single generic MCP tool for skill-mastery tracking.
Paceproof
4.5/10Verifies Ed25519-signed attestation records and builds audit reports via MCP tools.
Shimguard
4.5/10Wraps the ShimGuard CLI as a single generic MCP tool for agent-shim provenance checks.
Slop Eval
4.5/10Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Taskswarm
4.5/10Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.
Toolgovern
4.5/10Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
Truesignal
4.5/10Wraps the truesignal CLI as a single generic MCP tool for threat/connector status checks.
Truthroute
4.5/10Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Workspaceguard
4.5/10Wraps the WorkspaceGuard CLI as a single generic MCP tool for workspace usage checks.
Safe Fetch
4.5/10MCP server for fetching URLs, safe against SSRF, DNS rebinding, and redirect-to-internal attacks.
Rpgmaker Xp MCP
4.5/10Author RPG Maker XP games in natural language: read, write and render RGSS1 .rxdata.
Fleetpost MCP
4.5/10A mailbox for your machines: read fleet capabilities, send a request. Offline, no server.
Strimzi Kafka Cli
4.5/10Manage Apache Kafka on Kubernetes via Strimzi. Clusters, topics, users, connectors, MM2.
Attestari
4.5/10Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
Jobber MCP
4.5/10Read the Jobber Client Hub your service providers share: appointments, invoices and quotes
Nemesis Shield
4.5/10Positive-security for apps, APIs, LLMs and edge, plus fraud scoring and identity/AML screening.
Agent Identity MCP
4.5/10Gives an AI agent a disposable email and a real UK phone number to test signup flows.
Humanpen MCP
4.5/10Document-level AI humanizer for .docx/.pptx: whole file, selected passages, or flagged text.
Apex Psi MCP
4.5/10Cryptographic truth infrastructure for AI agents: seal, verify, anchor, cite, audit.
Better Workspace MCP
4.5/10Google Workspace MCP for Docs, Drive, Calendar, Gmail, Sheets, Slides, Tasks, Chat, People, Forms
Proventools
4.5/10Read-only ProvenTools business ideas, evidence, build prompts, and validation reports.
Oracle Feeds MCP
4.5/10On-chain price oracles: Chainlink (5 chains) + Pyth, staleness-flagged, no forced RPC key.
Cudaq Docs MCP
4.5/10CUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version.
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.