使用 DoWhy GCM 自动分配因果机制
AI agents use assign_causal_mechanisms to create or update resources in DoWhy MCP v2 0 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DoWhy MCP v2 0 environment.
The tool assigns (writes) causal mechanisms to a causal graph model, modifying its configuration. This is a reversible write operation — the model can be reconfigured — rather than destructive or executing external code. Severity is medium because misconfigured causal mechanisms could lead to incorrect downstream analyses, but the blast radius is limited to the model state.
From the tool's definition '自动分配因果机制' (automatically assign causal mechanisms) — assigns/sets causal mechanisms to nodes in a causal model graph
Attacks that exploit this kind of access
使用 DoWhy GCM 自动分配因果机制. It is categorised as a Write tool in the DoWhy MCP v2 0 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the DoWhy MCP v2 0 MCP server in PolicyLayer and add a rule for assign_causal_mechanisms: 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.
assign_causal_mechanisms is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the assign_causal_mechanisms 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 assign_causal_mechanisms. 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.
assign_causal_mechanisms 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 →