Agent-Blackbox MCP

driftguard_scan_secrets

Scans workspaces or supplied text for hardcoded API keys (OpenAI, Anthropic, Google, AWS, Stripe, GitHub, database URIs) to prevent accidental credential leaks.

Instructions

Scansiona il workspace o un testo per rilevare chiavi API hardcoded (OpenAI, Anthropic, Google, AWS, Stripe, GitHub, DB URI) per prevenire leak accidentali.

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": "driftguard_scan_secrets"
  }
}

Input Schema

Name	Required	Description	Default
`textOnly`	No	Testo facoltativo da ispezionare invece di scansionare l'intero workspace.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.0.0Nov 7, 2026

TDQS

B3.4/5.0

Behavior3/5

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

No annotations are supplied, so the description must carry the full behavioral burden: it discloses the detection catalog and the intended outcome (leak prevention), which is real value. It does not state that the scan is read-only/non-destructive, how deep the workspace traversal goes, or whether findings are reported only or acted upon.

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?

One front-loaded sentence with the verb and scope first and the detection list after. The seven-provider enumeration is long but each item carries information; no filler or repetition.

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?

For a one-optional-parameter scan tool with no output schema and no annotations, the description covers scope and targets but leaves the agent guessing what a scan returns (findings list, counts, locations) and whether scanning has side effects — information that would matter before invoking it.

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% and the single optional parameter textOnly is fully documented in the schema. The description mirrors that by saying it can scan 'il workspace o un testo', which clarifies the default workspace-wide behavior but adds no syntax or format detail beyond the schema.

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 concrete verb ('Scansiona') and resource (workspace or free text) and enumerates the secret classes it detects (OpenAI, Anthropic, Google, AWS, Stripe, GitHub, DB URI). An agent can distinguish it from siblings like driftguard_remediate_secret, though the description never names that sibling explicitly.

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 stated goal ('per prevenire leak accidentali') implies pre-commit or pre-export usage, and the two input modes are named. However, there is no explicit guidance on when to prefer this over driftguard_remediate_secret, driftguard_policy_check, or driftguard_network_check, and no exclusions or prerequisites are given.

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