使用 DoWhy GCM 从拟合的模型中采样
AI agents invoke draw_samples_from_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.
This tool executes a sampling procedure against a fitted Generative Causal Model (GCM), producing synthetic data. It does not merely read stored data but actively runs a computational process whose output depends on model state and arguments. No data is destroyed or money moved, but it executes an operation with potentially large compute/output side effects, placing it in Execute.
From the tool's definition '从拟合的模型中采样' (sample from fitted model) — triggers a computational sampling operation using the GCM model
Attacks that exploit this kind of access
使用 DoWhy GCM 从拟合的模型中采样. 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 draw_samples_from_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.
draw_samples_from_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 draw_samples_from_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 draw_samples_from_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.
draw_samples_from_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 →