Runs conda commands (list, info, env-list, create, remove, update) and returns structured JSON output.
Accepts file system path (path)
Part of the Python MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call conda 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.
Without a policy, an AI agent could call conda 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.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
conda:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Python policy for all 14 tools.
Runs conda commands (list, info, env-list, create, remove, update) and returns structured JSON output.. 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.
Add a rule in your Intercept YAML policy under the tools section for conda. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Python MCP server.
conda is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the conda 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.
Set action: deny in the Intercept policy for conda. 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.
conda 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.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept