AI agents call find_test_gaps to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only analysis tool that scans a codebase to identify testing coverage gaps. It returns information (which files lack tests) but performs no side effects, makes no modifications, executes no code, and creates no obligations. The blast radius of misuse is minimal — at worst, an agent could waste compute time scanning repositories, but no data is modified or destroyed.
From the tool's definition The tool 'find_test_gaps' is described as finding 'source files and symbols that have no corresponding tests' — a query/analysis operation that retrieves and reports information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Find source files and symbols that have no corresponding tests. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for find_test_gaps: 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 VibeServe. Nothing to install.
find_test_gaps 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 find_test_gaps 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 find_test_gaps. 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.
find_test_gaps is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →