Skip to main content
Glama
SLF Guardian MCP

SLF Guardian MCP

by slfguardian

audit_code

Statically scans source code before delivery or execution to flag RCE, data exfiltration, reverse shells, hard-coded secrets and unsafe patterns without running anything. Returns a pass/warn/review/block verdict with line-numbered findings.

Instructions

Audit source code before delivering or running it. Flags remote code execution (curl | bash), data exfiltration of environment variables or credential files, reverse shells, destructive commands, hidden base64 payloads, hard-coded secrets (AWS, OpenAI, Stripe, GitHub, database URLs), install-time hooks, typo-squatted package names and unsafe patterns such as shell=True, pickle.loads or TLS verification turned off. Nothing is executed; the audit is static text analysis. Returns a verdict (pass/warn/review/block), a safe_to_deliver flag and findings with line numbers.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoSource code to audit (single file or snippet).
pathNoOptional file name for the snippet.
filesNoSeveral files instead of one snippet.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it explicitly states 'Nothing is executed; the audit is static text analysis,' which is the single most important behavioral fact for a security-scanning tool. It also discloses the return shape (verdict levels, safe_to_deliver flag, findings with line numbers), though it does not explain how the four verdict tiers differ or what the agent should do on 'block'.

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?

Front-loaded with the action and timing, followed by a dense threat enumeration and a closing statement of the return contract. The long middle list is verbose but each item genuinely defines detection scope; the only cost is that the enumeration crowds out guidance on verdict handling.

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

Completeness4/5

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

For a three-parameter, read-only-in-effect analyzer with no output schema, the description supplies what matters: it is static, it does not execute, and it returns a verdict plus structured findings. The remaining gap is that the meaning of and appropriate response to each verdict tier is unstated.

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 description coverage is 100%, so code, path, and files are already documented. The description adds only the implicit notion of 'single file or snippet' versus multiple files, which the schema already conveys; it offers no additional semantics such as size limits or precedence when both code and files are supplied.

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?

States a specific verb and resource ('Audit source code') and enumerates the exact classes of problems it detects (RCE via curl|bash, exfiltration, reverse shells, hard-coded secrets, typo-squatting, unsafe patterns). The resource ('source code') implicitly separates it from check_command/check_domain/check_package/check_prompt, though no sibling is named explicitly.

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?

Gives a clear trigger: 'before delivering or running it,' which tells the agent this is a pre-flight gate on code artifacts. It does not state when NOT to use it or name the sibling tools to prefer for commands, domains, packages, or prompts, leaving that routing to inference.

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