Skip to main content
Glama

audit_server

Runs a runtime behavioral audit of an MCP server by exercising tools, resources, and prompts with canary inputs, capturing system calls, and detecting undeclared behavior or manifest rug-pulls.

Instructions

Run a runtime behavioral audit on an MCP server. Exercises tools, resources, and prompts using canary inputs, captures system calls (network, files, subprocesses), and detects undeclared behaviors or manifest rug-pulls.

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": {
      "command": "<command>"
    },
    "name": "audit_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
tracerNoauto
commandYes
timeoutNo
no_traceNo
transportNostdio
resolve_dnsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.7

TDQS

B3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the internal pipeline (canary inputs, syscall capture for network/files/subprocesses, undeclared-behavior and rug-pull detection), which is genuinely useful, but it omits the safety-critical facts: this executes an arbitrary command in a spawned process, and there is no warning about isolation, side effects, or runtime cost. For a tool that launches untrusted code with no annotation coverage, that is a significant gap.

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

Conciseness5/5

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

Two dense sentences with zero filler, front-loading the action and following with the mechanism and the outcome detected. Every clause adds information.

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

Completeness2/5

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

An output schema exists, so return values need not be explained. However, for a 6-parameter tool with zero schema coverage and no annotations, the description leaves the agent without guidance on how to invoke it correctly or what execution environment it requires.

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

Parameters2/5

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

Schema description coverage is 0% across 6 parameters, so the description must compensate and it does not — it never mentions command, transport, timeout, tracer, no_trace, or resolve_dns. Only 'command' and 'timeout' are guessable from their names; the meaning of tracer modes, transport selection, disabling tracing, and DNS resolution behavior is left entirely undocumented.

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

Purpose4/5

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

The description gives a specific verb and resource ('Run a runtime behavioral audit on an MCP server') and details the mechanism — exercising tools/resources/prompts with canary inputs and capturing system calls. The word 'runtime' implicitly contrasts with the static sibling inspect_manifest, but it never names that sibling, so differentiation is left to inference.

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

Usage Guidelines3/5

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

The first sentence implies when the tool applies (verifying a server's actual runtime behavior rather than its declared manifest), but there is no explicit when-to-use/when-not-to-use guidance, no statement about prerequisites (e.g., a sandbox, a runnable server command), and no named alternative to compare against.

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

Deploy Server

Other Tools