AgentAegis

scan_mcp_plugin

Scan MCP server code for supply-chain risks: exfiltration, prompt injection, dangerous capabilities, npm hooks, and secrets. Get a PROCEED/CAUTION/BLOCK verdict with findings.

Instructions

Scan an MCP server (git repo or code) for supply-chain risk BEFORE trusting it — exfiltration (secrets/env to the network), prompt-injection sinks, dangerous capabilities, npm install hooks, obfuscation, plus Semgrep + secret scanning → a PROCEED/CAUTION/BLOCK verdict with findings.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>"
    },
    "name": "scan_mcp_plugin"
  }
}

Input Schema

Name	Required	Description	Default
`source`	Yes
`previous_scan_id`	No	Optional. A prior scan_id (from agent_history) to record as this call's parent — builds a traversable chained-workflow lineage retrievable via agent_scan_get. Must be one of your own scans; ignored otherwise. Does not change this tool's analysis.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Jun 26, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It details the scanning actions (exfiltration, prompt-injection sinks, etc.) and the output (verdict with findings). It does not mention side effects or authorization requirements, but as a read-only scanner, the description is sufficiently transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense sentence that packs all key information (action, purpose, checks, output) upfront. It is efficient with no wasted words, though breaking it into shorter sentences could improve readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a complex input schema with nested objects and no output schema. While the description covers the scan's scope and verdict, it does not describe the return format or error scenarios, leaving gaps for an agent to fully understand the tool's output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% (the 'source' object's inner fields lack descriptions, while 'previous_scan_id' has one). The tool description does not add meaning beyond what the schema provides for the parameters; it focuses on tool functionality rather than parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('scan') and resource ('MCP server') and clearly enumerates the types of risks it checks for (exfiltration, prompt-injection, etc.), distinguishing it from sibling security tools that target different systems or vulnerabilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool ('BEFORE trusting it'), implying the context of vetting an MCP server. However, it does not provide explicit guidance on when not to use it or mention alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.