AI agents call point_in_time_diff 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 compares organizational graph snapshots to identify differences. It is purely informational and analytical, with no side effects on data. No resources are created, modified, deleted, or executed. The comparison of two static snapshots is a read-only operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool performs 'Diff org graph between two snapshots (or snapshot vs current)' — a comparison operation that retrieves and analyzes data without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
Diff org graph between two snapshots (or snapshot vs current). 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 point_in_time_diff: 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.
point_in_time_diff 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 point_in_time_diff 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 point_in_time_diff. 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.
point_in_time_diff 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 →