Scan and inspect an MCP server for security issues before connecting it: live tool-poisoning analysis, exposed-tool inventory + capabilities, TLS, and repo trust signals. Same engine as check_mcp_trust. Accepts a registry name, GitHub repo, or remote MCP URL.
| Name | Required | Description | Default |
|---|---|---|---|
| target | Yes | Registry name (io.github.x/y), GitHub repo (owner/repo), or remote MCP URL (https://...). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and it does disclose what the scan evaluates and that it is a pre-connect, inspect-style action. It remains vague about operational behavior such as whether the scan makes network calls, whether it can execute any tool logic, or what a result looks like.
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 tight sentences front-load purpose and capabilities with no filler; the sibling note is compact and adds context without bloating the description.
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?
For a single-parameter security scanner this is reasonably scoped, but there is no output schema and no hint of the returned report shape or side effects. The relationship to check_mcp_trust is mentioned but not resolved, leaving an important decision point incomplete.
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% and the schema already explains target as a registry name, GitHub repo, or remote MCP URL. The description restates these accepted formats without adding syntax details or constraints, so it stays at the baseline.
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 names a specific action ('scan and inspect an MCP server for security issues') and enumerates concrete capabilities such as live tool-poisoning analysis, the exposed-tool inventory, TLS, and repo trust signals. It does not, however, differentiate scan_mcp_server from its sibling check_mcp_trust beyond saying they share the same engine.
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?
It clearly frames when the tool is useful ('before connecting it') and states the accepted target forms. It falls short of explicit selection guidance: since check_mcp_trust is described only as the same engine, an agent cannot tell which tool to prefer in a given situation.
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.
Both tools accept identical inputs, run the same engine, and cover the same security-check workflow; check_mcp_trust and scan_mcp_server are near-duplicates. An agent cannot reliably determine which to call because the descriptions explicitly say they share the same engine and overlapping purposes.
Both names follow a verb_mcp_object snake_case pattern, so the naming convention is recognizable and mostly predictable. The minor inconsistency is that 'trust' is an abstract assessment object while 'server' is a concrete entity, and 'check'/'scan' are semantically close verbs.
Two tools for a narrow security-checking domain is borderline; the functionality could reasonably be a single tool. The count is not harmful, but it feels thin because the second tool mostly duplicates the first.
The pair covers the main input types (registry, GitHub repo, remote URL) and key security concerns such as tool-poisoning, capabilities, TLS, and repo trust. There are minor gaps such as no separate report retrieval or historical scan results, but those are not central to the stated purpose.