AI agents call wip_test_gap 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.
Without a complete description, classification is uncertain. The 'wip_' prefix suggests work-in-progress status. Based on context clues (sibling tools are primarily Read or analysis-focused), this is most likely a Read operation that queries or analyzes test coverage gaps. No indication of data modification, execution, deletion, or financial operations. Confidence is lower due to incomplete documentation.
From the tool's definition Tool name 'wip_test_gap' and description 'USE THIS for any' are both incomplete/uninformative. No action verbs or side effects are specified.
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_test_gap: 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_test_gap 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_test_gap 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_test_gap. 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_test_gap 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 →