✍️Writing & Content58🎨Image Generation71🎬Video & Animation120🎵Audio & Music100💬Chatbots & Assistants109💻Coding & Development444📈Marketing & SEO197⚡Productivity401🎯Design & UI/UX120📊Data & Analytics126📚Education & Research55💼Business & Finance174🏥Healthcare & Wellness22🔍Search & Knowledge20🤖AI Agent Infrastructure208🛡️AI Security & Testing32🧊3D & Spatial22🔎SEO Tools113🏡Real Estate7🗃️Data Extraction104🧠ADHD & Focus Tools11🔬Research & Academia45🧩LLM APIs & Models34⚙️Automation & Workflows45🔐Security & Privacy31📊Analytics & BI55⚖️Legal & Contracts14
Listed in AI Security & Testing with 47 other toolsPart of 4052+ curated AI tools on AISO
CuratedMCP logo

CuratedMCP

Open-source endpoint scanner that finds and grades every MCP server across your AI clients

0
freemiumA free open-source tier plus a self-serve team tier and an Enterprise option. Free is $0 forever for individual developers with no account required: the open-source MIT-licensed Hub, the shadow-MCP scan across every AI client with an A–F grade, install-once-sync-everywhere config management, Sentinel local policy guard in early access, TokenShield token ledger in beta, over 70 human-reviewed servers in the risk-classified catalog, and community support on Discord and GitHub. Team is $29 per seat per month, or $23 per seat billed annually, adding fleet-wide shadow-MCP inventory, an admin dashboard with allowlist push, an audit log of every MCP tool call, multi-IDE enforcement across Claude Code, Cursor, Windsurf, Copilot and Gemini, basic admin/member RBAC, and email support with a one-business-day SLA — self-serve, no sales call. A deployed-for-you option is published at $7,500 flat for a 60-day pilot that converts to per-seat only if it lands.View full pricing →

Visit CuratedMCP

curatedmcp.com
💰 View Detailed Pricing →Try CuratedMCP →

About CuratedMCP

CuratedMCP addresses a blind spot that appeared as soon as MCP took hold: servers are configured per-machine and per-client, which makes them invisible to any network-side AI gateway. CuratedMCP puts an open-source agent on the endpoint instead. One command discovers every MCP server configured across Claude Code, Claude Desktop, Cursor, Windsurf, GitHub Copilot and Gemini, flags the shadow servers nobody approved, and grades the machine A–F against a risk-classified catalog of over 70 human-reviewed servers — in roughly 60 seconds, entirely locally, with no configuration data leaving the machine and no account required. The scan exits non-zero on high-risk findings, which makes it usable directly as a CI gate rather than only as a report. The same catalog is queryable from an AI client via CuratedMCP's own MCP server, so an agent can check a server's risk classification before installing it. The Hub component installs a server once and syncs it across every client, replacing the per-client config sprawl that causes shadow servers in the first place. Two further components are in earlier stages: Sentinel, a local policy guard in early access, and TokenShield, a measured token ledger in beta. The product is MIT licensed and free for individual developers; the commercial tier is fleet-wide visibility, an org allowlist pushed to every machine, and an audit log of MCP tool calls for engineering organisations.

Does ChatGPT recommend your AI tool?

If you're building in AI Security & Testing, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.

Scan my tool — free →Track it monthly — 7 days free →

then $19/mo · cancel anytime

Key Features

✓One-command discovery of MCP servers across six AI clients
✓A–F machine grade against a risk-classified catalog of 70+ reviewed servers
✓Runs locally; no config data leaves the machine, no account needed
✓Non-zero exit on high-risk findings for use as a CI gate
✓Catalog queryable from an AI client via CuratedMCP's own MCP server
✓Hub installs a server once and syncs it to every client

CuratedMCP Pros & Cons

✅ Pros

  • +Endpoint vantage point sees what a network gateway structurally cannot
  • +MIT licensed and free for individuals, with no account gate on the scan
  • +CI-friendly exit codes make it enforceable, not just informational

⚠️ Cons

  • −Sentinel is early access and TokenShield is beta, so enforcement is immature
  • −Catalog coverage of 70+ servers is small relative to the MCP ecosystem
  • −Six supported clients means unusual or in-house agent runtimes are missed

Tags

mcpsecurityshadow-itopen-sourceauditdeveloper-tools
🏷️

Is CuratedMCP your tool?

This is the page buyers and AI assistants read when they look up CuratedMCP. Claim your listing for $19 one-time — no subscription, nothing to cancel — and take a capped slot in your category: each one sells a fixed number, and yours ranks above every free tool in it, with a Featured badge. Prefer it ongoing? Monthly is one click away on the next page.

Claim it — $19 once →
💡

Complete Your Security Stack

Other security tools in our catalog:

1Password

Try Free

Secrets and credential manager

Keep API keys and .env secrets out of your repo

$2.99/mo+Learn more →

Gamma

Try Free

AI presentation builder

Turn ideas into polished decks instantly

Free tier, $10/mo+Learn more →

AdCreative.ai

Try Free

AI-powered ad creatives

Generate marketing visuals in seconds

$29/mo+Learn more →

💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.

Stay updated on AI Security & Testing tools — join our weekly newsletter

One concise email with fresh launches, trending picks, and featured standouts.

Alternatives to CuratedMCP

View all CuratedMCP alternatives →

LangSmith

LLMOps platform for debugging and monitoring LLM apps.

freemium

Sentry

Error tracking and performance monitoring for developers

freemium

More AI Security & Testing tools

CASPERWASP

AI-powered document, PDF intelligence, and business design platform.

Vibe App Scanner

Attack-grade security scanning for AI-built apps with agent-ready fixes over MCP and weekly monitoring, first scan free, from $19/mo

Xalgorix

An open-source autonomous AI pentester that proves every finding with a working exploit before reporting it, and gates CI on verified results — from $16/mo

CyberScore Labs

Enter your website address and get a free private report in 60 seconds showing what hackers can see.

Decripte

AI-native cyber incident detection and end-to-end response with governed automation and expert 24/7 support.

DepScope

Free keyless MCP server that catches hallucinated, vulnerable, and typosquatted packages

Agent connectivity: not yet verified