Skip to main content
Glama
mcp-security-auditor

mcp-security-auditor

by jashory

scan_path

Audit a local directory or file using static Python AST, MCP schema, prompt-injection, and Firebase rules checks; secrets are redacted by default.

Instructions

Run static Python AST, MCP schema, prompt-injection, and Firebase rules security scan on a local directory or file (secrets redacted by default).

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": {
      "target": "<target>"
    },
    "name": "scan_path"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNojson
targetYesLocal directory or file path to audit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.3.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries the full burden. It does disclose two behavioral traits: the scan is static and secrets are redacted by default, which is valuable. But 'redacted by default' implies a toggle that no parameter exposes, and the description never says the scan is read-only/non-mutating, whether Firebase rules scanning needs credentials or network access, or how long a scan may take.

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?

One front-loaded sentence that starts with the action and enumerates scope without filler. Every clause (scan types, target type, redaction) contributes information.

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 is simple (2 params, no nested objects, no annotations) so not much is required, but with no output schema the description should say something about what a scan returns (findings list, severity, SARIF/markdown output). The dangling 'redacted by default' without a corresponding parameter also leaves a loose end.

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 coverage is 50%: 'target' is documented in the schema while 'format' (json/markdown/sarif, default json) has no description anywhere. The description adds nothing about either parameter — not output format implications, not whether target may be a glob or symlink. The enum values are largely self-explanatory, which keeps this from being a 1.

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?

Specific verb ('Run ... security scan') plus a concrete resource ('local directory or file'), and the scan families (Python AST, MCP schema, prompt-injection, Firebase rules) make the scope unmistakable. It does not explicitly contrast with siblings like remediate_path, but the verb/resource pairing is clear enough to distinguish a read-oriented audit from a remediation tool.

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?

Usage is only implied: the phrase 'on a local directory or file' bounds where it applies (local paths, not remote repos), which is a useful constraint. There is no explicit when-to-use vs. remediate_path guidance, no prerequisites, and no statement of what the tool will not do.

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