使用 DoWhy GCM 独立性检验
AI agents call independence_test_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 statistical independence testing as part of causal inference analysis. It reads data, computes test statistics, and returns results—a pure analytical operation with no side effects, no external execution, no data modification, and no destructive or financial impact. Even if misused by an AI agent, it can only produce incorrect statistical outputs, not cause damage to systems or data.
From the tool's definition Tool name 'independence_test_gcm' and description indicating statistical testing (检验 = test/testing) with GCM.
Attacks that exploit this kind of access
使用 DoWhy GCM 独立性检验. 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 independence_test_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.
independence_test_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 independence_test_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 independence_test_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.
independence_test_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 →