使用 DoWhy GCM 估计平均因果效应
AI agents call average_causal_effect_gcm to retrieve information from DoWhy MCP v2 0 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs causal effect estimation, which is a read/query operation that calculates a numerical result from an existing causal model. It does not modify data, execute external commands, delete anything, or involve financial transactions. The description is brief and in Chinese, slightly lowering confidence, but 'estimate' operations are consistently read-category.
From the tool's definition '估计平均因果效应' (estimate average causal effect) — the tool estimates/computes a statistical quantity from a causal model
Attacks that exploit this kind of access
使用 DoWhy GCM 估计平均因果效应. It is categorised as a Read tool in the DoWhy MCP v2 0 MCP Server, which means it retrieves data without modifying state.
Register the DoWhy MCP v2 0 MCP server in PolicyLayer and add a rule for average_causal_effect_gcm: 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.
average_causal_effect_gcm 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 average_causal_effect_gcm 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 average_causal_effect_gcm. 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.
average_causal_effect_gcm 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 →