Runs a defensive, read-only security audit of the local machine for MCP and AIagent risks: risky bindings, MCP config issues, and confused-deputy exposu re.Use before enabling MCP servers or when the user says audit mcp, check lo calhost exposure, mcp security. Outputs text, JSON, SARIF, or HTML. Triggers : audit mcp, mcp security, defensive-mcp-audit.
SkillScore91Maintained
Automatic
◆Security & AppSec pack
Last verified 8/15/2026
What it changes
Passed 20 of 22 test cases with the skill, and 9 of 22 without it.
Without skill41%
With skill91%
Checks it passed that the model alone missed
References mcp-tool-scout integration.
Executes python3 -m defensive_mcp_audit.
Restricts inspection to read-only inventory.
and 9 more in the full report
12 fixed8 passed either way1 still failing1 broke
Pass-rate lift
+50 pp
Tokens
-20%
Agent turns
0%
Response time
-33%
Model gemini-3.6-flashMeasured 8/15/2026v220 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 12
Prompt
What open source project and license underlying tool wraps the defensive MCP auditing capabilities?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies the underlying project as Stijnman defensive-mcp-audit.
Missed
Passed
case-15 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md57 linessingle file
Defensive MCP Audit
When to Use
User says audit mcp or task matches this capability
User says mcp security or task matches this capability
User says localhost exposure or task matches this capability
User says defensive-mcp-audit or task matches this capability
Workflow
Confirm audit is read-only; no port scanning beyond localhost inventory.