使用 DoWhy 验证因果图
AI agents call causal_graph_validator 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.
Validation tools typically read and analyze input without producing side effects. The tool appears to check the integrity or correctness of a causal graph structure. No write, execute, or destructive behavior is implied. Confidence is moderate because the description is minimal and in Chinese, leaving some ambiguity about whether it modifies state.
From the tool's definition '验证因果图' means 'validate causal graph' in Chinese — a validation/check operation that reads and assesses a graph structure without modifying data
Attacks that exploit this kind of access
使用 DoWhy 验证因果图. 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 causal_graph_validator: 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.
causal_graph_validator 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 causal_graph_validator 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 causal_graph_validator. 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.
causal_graph_validator 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 →