Skip to main content
Glama
Sign In
guardvibe

guardvibe

by goklab
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

deep_scan

Analyze code with LLM-powered security review to uncover IDOR, business logic flaws, race conditions, auth bypass, and privilege escalation that pattern-matching misses.

Instructions

LLM-powered deep security analysis for vulnerabilities that pattern-matching cannot detect: IDOR, business logic flaws, race conditions, stale auth, mass assignment, privilege escalation. Defaults to Claude Haiku 4.5 (~cents per scan); pass model: 'sonnet' for deeper analysis at higher cost. Requires ANTHROPIC_API_KEY or OPENAI_API_KEY env var.

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": {
      "code": "<code>",
      "language": "<language>"
    },
    "name": "deep_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesCode to analyze
focusNoFocus area — narrows the prompt to a specific vulnerability classall
modelNoLLM model. haiku = fast & cheap (default), sonnet = deeper analysishaiku
formatNoOutput formatmarkdown
contextNoAdditional context (e.g., 'This is a payment endpoint')
languageYesProgramming language
maxBytesNoMax prompt size in bytes — caps cost. Code over this limit is truncated.
existingFindingsNoAlready-detected findings to avoid duplicating

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.66.0
    • removedInput schema / additionalProperties
      Removed value: -false
  2. Addedv3.35.1
  3. Removedv3.30.0
  4. Addedv3.0.42

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses cost ('~cents per scan'), the auth requirement (ANTHROPIC_API_KEY / OPENAI_API_KEY), and the truncation behavior tied to maxBytes. It stops short of describing return structure or failure modes, but the operational context is solid.

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?

Three tightly packed sentences, front-loaded with the distinguishing capability, then cost/model guidance, then the prerequisite. No wasted phrasing.

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 an 8-param tool with full schema coverage and no output schema, the description supplies the key missing operational facts (cost, auth, model choice). Return-shape expectations are somewhat unaddressed, but the format enum covers output form adequately.

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 the schema already documents all 8 parameters. The description adds model-cost tradeoff context but largely repeats what the schema conveys, so the baseline 3 applies.

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?

States a specific verb+resource (LLM-powered deep security analysis) and enumerates exactly the vulnerability classes it targets (IDOR, business logic, race conditions, etc.). This clearly distinguishes it from pattern-matching siblings like check_code or scan_file.

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 framing 'vulnerabilities that pattern-matching cannot detect' implicitly tells the agent when to reach for this instead of the pattern-based siblings, and the model guidance (haiku default vs sonnet for depth) aids selection. It doesn't explicitly name alternative tools or state when NOT to use it, keeping it short of a 5.

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