使用 DoWhy GCM 评估因果模型
AI agents call evaluate_causal_model_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.
Evaluating a causal model is a read/analysis operation: it assesses the fit or quality of a causal model against data using DoWhy GCM. No data is created, modified, deleted, or executed externally. The description is minimal (translated: 'Evaluate causal model using DoWhy GCM'), lowering confidence slightly, but 'evaluate' consistently implies a read-only diagnostic operation in causal inference contexts.
From the tool's definition 'evaluate_causal_model_gcm' — the term 'evaluate' implies assessment/analysis of an existing causal model rather than modification or execution of external operations
Attacks that exploit this kind of access
使用 DoWhy GCM 评估因果模型. 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 evaluate_causal_model_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.
evaluate_causal_model_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 evaluate_causal_model_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 evaluate_causal_model_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.
evaluate_causal_model_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 →