使用 DoWhy GCM 测试机制变化
AI agents invoke mechanism_change_test_gcm to trigger actions in DoWhy MCP v2 0. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a statistical hypothesis test on causal mechanisms using DoWhy's GCM framework. It does not merely retrieve stored data (it runs a test/computation), nor does it write, delete, or involve finances. The description is brief and in Chinese with no detail on side effects, which lowers confidence slightly.
From the tool's definition '测试机制变化' (test mechanism change) using DoWhy GCM — runs a statistical test/analysis over causal graph mechanisms
Attacks that exploit this kind of access
使用 DoWhy GCM 测试机制变化. It is categorised as a Execute tool in the DoWhy MCP v2 0 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DoWhy MCP v2 0 MCP server in PolicyLayer and add a rule for mechanism_change_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.
mechanism_change_test_gcm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the mechanism_change_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 mechanism_change_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.
mechanism_change_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 →