使用 DoWhy GCM 拟合因果模型
AI agents use fit_gcm_model 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.
This tool fits (trains/creates) a Graphical Causal Model (GCM), which modifies the state by generating a new model object. This is a Write operation because it creates a reversible data artifact (a model that can be discarded or replaced). It does not execute arbitrary code with unpredictable effects (Execute), is not destructive, and has no financial impact.
From the tool's definition Tool name 'fit_gcm_model' and description '使用 DoWhy GCM 拟合因果模型' (Fit a causal model using DoWhy GCM) indicate the tool creates/builds a causal model artifact.
Attacks that exploit this kind of access
使用 DoWhy GCM 拟合因果模型. 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 fit_gcm_model: 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.
fit_gcm_model 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 fit_gcm_model 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 fit_gcm_model. 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.
fit_gcm_model 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 →