AI agents call wip_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.
Based on sibling tools (cross_layer_flow_map, cross_org_diff, dead_code_audit, export_sarif), this server primarily performs analysis and comparison of Salesforce metadata. 'wip_diff' most likely compares work-in-progress code or configuration without modifying it. The incomplete description lowers confidence, but the pattern of analytical tools and the 'diff' terminology suggest read-only comparison operations.
From the tool's definition Tool name 'wip_diff' suggests a diff/comparison operation. Description is incomplete ('USE THIS for any') with no actionable details about what data it accesses or modifies.
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 wip_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.
wip_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 wip_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 wip_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.
wip_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 →