Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@curatedmcp/mcp check if @modelcontextprotocol/server-filesystem is verified"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that exposes the CuratedMCP catalog — search human-reviewed, risk-classified MCP servers, check whether a server is verified, and pull its full risk/capability profile, all from inside any MCP client.
npx -y @curatedmcp/mcpBefore installing an unfamiliar npx some-mcp-server command, ask your AI agent to check it against the catalog first — no need to leave the conversation.
Related MCP server: mcp-registry-finder
Tool | What it does |
| Search the catalog by keyword and/or category |
| Full risk profile for one server: risk level, declared capabilities (file access, network egress, shell exec, etc.), compatible clients, transport type, install command |
| Quick check: is this server name or npm package in the verified catalog? |
{
"mcpServers": {
"curatedmcp": {
"command": "npx",
"args": ["-y", "@curatedmcp/mcp"]
}
}
}npm install
npm run build
node test/smoke.mjs # exercises all three tools against curatedmcp.comBy default the server calls the production API at https://curatedmcp.com. Override with CURATEDMCP_APP_URL for local development against a different deployment.
Quick lookup: given a server name or its npm package (e.g. '@org/some-mcp-server'), report whether it's in the CuratedMCP verified catalog. Useful right before running an unfamiliar npx <package> MCP server install command.
Inputs: nameOrPackage (required).
Fetch the full risk profile for a single MCP server in the CuratedMCP catalog: risk level, declared capabilities (file access, network egress, shell exec, etc.), compatible clients, transport type, and install command.
Inputs: slug (required).
Search the CuratedMCP catalog of human-reviewed, risk-classified MCP servers by keyword and/or category. Use this before installing an unfamiliar MCP server to see if a vetted alternative already exists.
Inputs: limit, query, category.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a clearly distinct purpose: verifying existence, fetching full details, and searching the catalog. No overlap in functionality.
All tool names follow a consistent verb_noun pattern (check_, get_, search_) with snake_case, making them predictable and easy to understand.
With 3 tools, the set is well-scoped for querying a catalog, fitting within the ideal 3-15 range. Each tool serves a necessary function without redundancy.
The toolset covers the core use cases for interacting with a curated MCP server catalog: verifying a server, getting detailed risk profiles, and searching. No obvious gaps for its intended purpose.
Search 70,510 indexed MCP servers, install-risk scoring and Ed25519-signed Agent Trust Cards.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
