AI agents invoke lint to trigger actions in Python. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a linting process (e.g., ruff) against code. While linting is typically read-only in effect, it runs external commands whose behavior depends on arguments, placing it in the Execute category. Misuse could lead to unintended code analysis or exposure of code details, but blast radius is moderate.
From the tool's definition 'Runs' — the description begins with 'Runs', indicating the tool executes an external process (likely ruff or a similar linter based on server context of structured Python tool output).
Attacks that exploit this kind of access
Runs. It is categorised as a Execute tool in the Python MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Python MCP server in PolicyLayer and add a rule for lint: 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.
lint is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the lint 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.
Set action: deny in the PolicyLayer policy for lint. 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.
lint 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.
lint is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →