poetry

Runs Poetry commands and returns structured output. Supports install, add, remove, show, build, update, lock, check, and export actions.

Accepts file system path (path); High parameter count (13 properties)

Part of the Python MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

@paretools/python Destructive Risk 5/5

// WHEN AI AGENTS USE THIS TOOL

AI agents may call poetry to permanently remove or destroy resources in Python. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON POETRY

Without a policy, an AI agent could call poetry in a loop, permanently destroying resources in Python. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

io-github-dave-london-pare-python.yaml

tools:
  poetry:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full Python policy for all 14 tools.

// DETAILS

Tool Name poetry

Category Destructive

MCP Server Python MCP Server

Risk Level Critical

// MORE PYTHON TOOLS

Destructive conda Execute uv-run Write pip-install Write uv-install Read black Read mypy Read pip-audit Read pip-list

View all 14 tools →

// RELATED READING

// FAQ

What does the poetry tool do? +

Runs Poetry commands and returns structured output. Supports install, add, remove, show, build, update, lock, check, and export actions.. It is categorised as a Destructive tool in the Python MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on poetry? +

Add a rule in your Intercept YAML policy under the tools section for poetry. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Python MCP server.

What risk level is poetry? +

poetry is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit poetry? +

Yes. Add a rate_limit block to the poetry rule in your Intercept 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 poetry completely? +

Set action: deny in the Intercept policy for poetry. 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 poetry? +

poetry is provided by the Python MCP server (@paretools/python). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

poetry

Enforce policies on Python