AI agents invoke uv-run 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.
This tool executes arbitrary commands within a uv (Python package manager) managed environment. While the output is structured as JSON, the underlying action is command execution—a core Execute category behavior.
From the tool's definition Runs a command in a uv-managed environment and returns structured output. The tool explicitly performs command execution via 'uv-run' which triggers external operations with effects dependent on the command arguments passed.
Attacks that exploit this kind of access
Runs a command in a uv-managed environment and returns structured output. 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 uv-run: 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.
uv-run 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 uv-run 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 uv-run. 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.
uv-run 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.
uv-run 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 →