使用 DoWhy 测量总因果影响（直接+间接）
AI agents call total_causal_influence 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.
The tool measures/quantifies causal influence using DoWhy, which is a read/analysis operation. It computes statistical estimates from data without creating, modifying, executing, or deleting anything. Consistent with sibling tools like 'average_causal_effect_gcm' and 'arrow_strength_gcm' which are also analytical. Severity is low since misuse would at worst produce misleading causal estimates, not cause system harm.
From the tool's definition '测量总因果影响（直接+间接）' — 'measure total causal influence (direct+indirect)'; this is an analytical/measurement operation with no side effects
Attacks that exploit this kind of access
使用 DoWhy 测量总因果影响（直接+间接）. 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 total_causal_influence: 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.
total_causal_influence 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 total_causal_influence 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 total_causal_influence. 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.
total_causal_influence 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 →