mcp_call_conda_info
AI agents call mcp_call_conda_info to retrieve information from Mcp My Mac without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve conda package and environment metadata without modifying or executing arbitrary operations. It reads system state for debugging purposes. The empty description lowers confidence slightly, but the naming pattern and server context strongly suggest a read-only diagnostic function typical of conda info commands.
From the tool's definition Tool name 'conda_info' suggests it queries conda environment information. The sibling tools (gpu_available, mac_system_profiler) are diagnostic/informational queries.
Attacks that exploit this kind of access
mcp_call_conda_info. It is categorised as a Read tool in the Mcp My Mac MCP Server, which means it retrieves data without modifying state.
Register the Mcp My Mac MCP server in PolicyLayer and add a rule for mcp_call_conda_info: 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 Mcp My Mac. Nothing to install.
mcp_call_conda_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mcp_call_conda_info 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 mcp_call_conda_info. 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.
mcp_call_conda_info is provided by the Mcp My Mac MCP server (zhongmingyuan/mcp-my-mac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →