pip-audit

Runs pip-audit and returns a structured vulnerability report.

SERVERPython SOURCEDave-London/Pare

Low RISK CLASS

Category Read

Parameters 120 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-dave-london-pare-python/pip-audit.md

WHAT IT DOES

What pip-audit does on Python

AI agents call pip-audit to retrieve information from Python without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameter	Type	Required	Description
`fix`	boolean	—	Auto-remediate vulnerabilities (--fix)
`path`	string	—	Project root path
`local`	boolean	—	Only audit packages in the local virtualenv (-l, --local)
`dryRun`	boolean	—	Preview fix changes without applying (--dry-run)
`noDeps`	boolean	—	Skip auditing dependencies (--no-deps)
`strict`	boolean	—	Fail on skipped dependencies (-S, --strict)
`compact`	boolean	—	Prefer compact output
`indexUrl`	string	—	Custom package index URL for corporate/private registry support
`ignoreVuln`	array	—	Vulnerability IDs to suppress (e.g. PYSEC-2023-001)
`requirements`	string	—	Path to requirements file
`skipEditable`	boolean	—	Skip auditing editable packages (--skip-editable)
`vulnerabilityService`	string	—	Vulnerability service to query (default: pypi)

Parameters from the server's own tool schema.

RISK

Why pip-audit is rated Low

pip-audit is a passive vulnerability scanner that analyzes dependencies and produces a report. It retrieves and queries vulnerability data but does not install, uninstall, upgrade, downgrade, or otherwise modify packages; it performs no code execution or destructive actions. The output is informational only, making this a Read operation with low severity.

From the tool's definition pip-audit "runs pip-audit and returns a structured vulnerability report" — this is a read-only security scanning tool that queries installed packages for known vulnerabilities without modifying, executing code, or making changes to the system.

Risk signalsAccepts file system path (path) · High parameter count (12 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs pip-audit safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Python, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pip-audit, this is the rule to start with:

pip-audit Allowed

pip-audit is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "pip-audit": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Python, apply this rule, and every pip-audit call is checked against it from then on.

FAQ

Questions about pip-audit

What does the pip-audit tool do? +

Runs pip-audit and returns a structured vulnerability report. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.

What parameters does pip-audit accept? +

pip-audit accepts 12 parameters: fix, path, local, dryRun, noDeps, strict, compact, indexUrl, ignoreVuln, requirements, skipEditable, vulnerabilityService. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on pip-audit? +

Register the Python MCP server in PolicyLayer and add a rule for pip-audit: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Python. Nothing to install.

What risk level is pip-audit? +

pip-audit is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit pip-audit? +

Yes. Add a rate_limit block to the pip-audit rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block pip-audit completely? +

Set action: deny in the PolicyLayer policy for pip-audit. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides pip-audit? +

pip-audit is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Python, and thousands of servers like it.

This server

All 14 Python tools →

Across the catalogue

emit_second_audit on 0sec → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →