使用 DoWhy GCM RCA异常评分器
AI agents call rca_scorer_gcm 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 performs root cause analysis scoring, which is a read/analytical operation that queries and computes attribution scores from a causal model without modifying data or executing external operations. Severity is medium because causal inference results could influence significant decisions, but the tool itself only reads and computes.
From the tool's definition 'RCA异常评分器' translates to 'RCA anomaly scorer' — scoring/analysis function that computes root cause analysis scores using DoWhy GCM
Attacks that exploit this kind of access
使用 DoWhy GCM RCA异常评分器. 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 rca_scorer_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.
rca_scorer_gcm 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 rca_scorer_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 rca_scorer_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.
rca_scorer_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 →