Phase 2 – Option B:
AI agents call scan_repository to retrieve information from Local Testing Agent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries repository structure and test metadata to support test discovery and planning. While it accesses file systems and code artifacts, it performs no writes, deletions, executions, or financial operations.
From the tool's definition Tool name is 'scan_repository' and description indicates it performs 'Phase 2 – Option B' within a testing automation context.
Attacks that exploit this kind of access
Phase 2 – Option B:. It is categorised as a Read tool in the Local Testing Agent MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Local Testing Agent MCP Server MCP server in PolicyLayer and add a rule for scan_repository: 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 Local Testing Agent MCP Server. Nothing to install.
scan_repository 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 scan_repository 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 scan_repository. 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.
scan_repository is provided by the Local Testing Agent MCP Server MCP server (marcelkurvers/local-testing-agent). 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 →