AI agents call list_findings to retrieve information from Repomend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists security findings from a vulnerability management system. The action is purely informational—it reads data filtered by various criteria but produces no side effects, modifications, or irreversible changes. It belongs in the Read category with low severity because exposure poses minimal risk; the worst case is disclosure of vulnerability metadata already known to the team.
From the tool's definition Tool name 'list_findings' and description 'List security findings for your team, filtered by severity/status/scanner' indicate querying and retrieval of existing security scan results with no modification, creation, or deletion.
Attacks that exploit this kind of access
List security findings for your team, filtered by severity/status/scanner. It is categorised as a Read tool in the Repomend MCP Server, which means it retrieves data without modifying state.
Register the Repomend MCP server in PolicyLayer and add a rule for list_findings: 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 Repomend. Nothing to install.
list_findings 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 list_findings 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 list_findings. 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.
list_findings is provided by the Repomend MCP server (repomend-dev/mcp). 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 →