scan_mcp_serverRun a full MCPCheckup scan against a remote MCP server: handshake, protocol version, tool/resource/prompt inventory, security heuristics, network/TLS posture, and license info.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The MCP server endpoint to scan, e.g. https://example.com/mcp |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses all major activities of the scan (handshake, inventory, security heuristics) without causing ambiguity. No annotations contradict description, but it does not mention network requirements or potential side effects.
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 with front-loaded action verb. No redundant or unnecessary information.
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 single parameter, no output schema, and sibling tool, description sufficiently explains what the tool does and what it covers. Lacks explicit mention of return format but still adequate.
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 covers 100% of parameters with description for 'url'. The description adds minor context ('remote MCP server' vs 'endpoint'), but does not significantly expand on the schema. Baseline 3 is appropriate.
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?
Clearly states verb 'Run a full MCPCheckup scan' and resource 'remote MCP server', listing specific components (handshake, protocol version, etc.). Distinguishes from sibling tool 'create_scorecard' by focusing on scanning rather than scorecard creation.
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?
Implied usage for scanning an MCP server, but no explicit guidance on when to use versus create_scorecard or alternatives. No exclusions or prerequisites provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The two tools have distinct purposes: scan_mcp_server returns raw scan data, while create_scorecard returns a formatted scorecard with a URL and image. They are related but not ambiguous, though an agent might mistakenly think create_scorecard performs the scan internally.
Both tools follow a consistent verb_noun pattern: 'create_scorecard' and 'scan_mcp_server'. The naming is clear and predictable.
With only 2 tools, the server feels sparse but may be acceptable for a focused service. A broader set like listing or deleting scorecards could be expected, but the count is not extreme.
The server lacks tools for retrieving, updating, or deleting scorecards or scans. After creating a scorecard, there is no way to access it later without re-running, which is a significant gap.