使用 DoWhy 和 causal-learn 运行 PC 算法进行因果发现
AI agents invoke pc_algorithm to trigger actions in DoWhy MCP v2 0. 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.
The tool executes the PC (Peter-Clark) causal discovery algorithm, which runs a computational process over provided data to infer causal structure. This is an Execute-category action as it triggers an external algorithm/operation whose effects depend on the input data and parameters. It does not read pre-existing stored data, write persistent records, or perform destructive/financial actions.
From the tool's definition '运行 PC 算法进行因果发现' (run PC algorithm for causal discovery) — triggers an external computational algorithm using causal-learn and DoWhy libraries
Attacks that exploit this kind of access
使用 DoWhy 和 causal-learn 运行 PC 算法进行因果发现. It is categorised as a Execute tool in the DoWhy MCP v2 0 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DoWhy MCP v2 0 MCP server in PolicyLayer and add a rule for pc_algorithm: 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 DoWhy MCP v2 0. Nothing to install.
pc_algorithm 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 pc_algorithm 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 pc_algorithm. 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.
pc_algorithm is provided by the DoWhy MCP v2 0 MCP server (lesong36/dowhy_mcp). 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 →