AI agents call governor_risk_check to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or analyze governor limit violations and risks within a Salesforce org—a query/read operation with no side effects. The incomplete description reduces confidence slightly, but context from related analysis tools and the 'check' verb (indicating assessment rather than action) supports classification as Read rather than Execute.
From the tool's definition Tool name 'governor_risk_check' and context as part of a Salesforce knowledge graph analysis suite suggests it queries/analyzes existing data (governor limits, risks) rather than modifying or executing operations.
Attacks that exploit this kind of access
USE THIS for any. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for governor_risk_check: 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 Sfgraph. Nothing to install.
governor_risk_check 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 governor_risk_check 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 governor_risk_check. 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.
governor_risk_check is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →