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: mcpcatalogs
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.
| Name | Required | Description | Default |
|---|---|---|---|
| nameOrPackage | Yes | Server display name or npm package name to check |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations; description says it's a quick lookup reporting verification status. Lacks details on error handling, response format, or any side effects. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with 'Quick lookup'. Every sentence earns its place—no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose, use case, and parameter. Missing explicit return value description, but for a simple boolean lookup, description is largely complete. Output schema absent reduces burden.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Single parameter nameOrPackage is described in schema; description adds clarifying example (@org/some-mcp-server) and restates acceptable inputs. Adds value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clear verb ('check'/'report') and resource (verification status in CuratedMCP catalog). Distinguishes from siblings by focusing on quick lookup vs details or search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
States when to use ('right before running an unfamiliar npx MCP server install command'). No explicit when-not-to-use or sibling comparison, but context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The server's slug or id, e.g. 'github-mcp' — get this from search_mcp_catalog |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses what data is returned but lacks details on side effects (none expected), permissions, or rate limits. Adequate for a simple fetch operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single well-structured sentence that front-loads the action and resource, lists contents in a readable list, and has no filler or unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 param, no output schema, no nested objects), the description adequately lists return fields. Could mention read-only nature but is largely complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (one param slug described). The param description already explains slug source; the tool description adds a helpful cross-reference to the search tool, adding value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it fetches the full risk profile for a single MCP server, specifies exact contents (risk level, capabilities, etc.), and implicitly distinguishes from siblings like search_mcp_catalog by focusing on a single item.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after search via the parameter note 'get this from search_mcp_catalog', but does not explicitly state when to use this versus check_mcp_server_verified or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results, default 10 | |
| query | No | Free-text search — matches name, tagline, or tags | |
| category | No | Filter by category slug, e.g. 'developer-tools', 'databases' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose behavioral traits such as read-only nature (implied but not stated), authentication requirements, rate limits, or what happens on no results. The description only states 'Search', which is minimal for a tool with no annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with only two sentences, front-loaded with the action and resource, and every sentence earns its place. No redundant or verbose language.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (3 optional parameters, no output schema) and the presence of siblings, the description is mostly complete. It explains the purpose and usage context. However, it could be improved by briefly noting the return format or behavior (e.g., 'returns a list of matching servers with basic info').
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description adds context by stating 'by keyword and/or category', which maps to query and category parameters, but does not add deeper meaning beyond what the schema already provides for each parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Search' and identifies the resource as the 'CuratedMCP catalog of human-reviewed, risk-classified MCP servers'. It also distinguishes from siblings by stating a use case ('before installing an unfamiliar MCP server') which hints at differentiation from check_mcp_server_verified and get_mcp_server_details.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use this tool: 'Use this before installing an unfamiliar MCP server to see if a vetted alternative already exists.' It provides clear context but lacks explicit exclusions or alternatives for when not to use it, which would push it to a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0check_mcp_server_verifiedget_mcp_server_detailssearch_mcp_catalogScored 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, 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.
Search and get install details on MCP servers, right from your agent -- a unified marketplace index.
