Runs conda commands (list, info, env-list, create, remove, update) and returns structured JSON output.
AI agents invoke conda to trigger actions in Test. 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 conda commands including environment creation, removal, and package updates. 'remove' can irreversibly delete environments/packages (Destructive), but since it also covers non-destructive operations and the primary framing is 'runs commands', Execute is the appropriate category.
From the tool's definition Runs conda commands (list, info, env-list, create, remove, update)
Documented attack patterns abuse exactly the kind of access conda gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Test, and nothing reaches the server without passing your rules. This is the rule we recommend for conda:
{
"version": "1",
"default": "deny",
"tools": {
"conda": {
"limits": [
{
"counter": "conda_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}conda stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Runs conda commands (list, info, env-list, create, remove, update) and returns structured JSON output. It is categorised as a Execute tool in the Test MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Test MCP server in PolicyLayer and add a rule for conda: 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 Test. Nothing to install.
conda 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 conda 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 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 Test MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Test, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
202 Test tools catalogued and risk-classified — across an index of 43,000+ MCP servers.