search_evidence
AI agents call search_evidence to retrieve information from RobotWS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'search_evidence' indicates a search/query operation typical of information retrieval. Given the RobotWS server stores metadata in SQLite and provides context for test case generation, this tool likely queries indexed data to find evidence or references without modifying state. No evidence of write, execute, destructive, or financial capabilities.
From the tool's definition Tool name 'search_evidence' combined with server purpose of indexing and querying Robot Framework/Python files and SQLite metadata suggests a retrieval/query operation. The description is empty, which lowers confidence slightly.
Attacks that exploit this kind of access
search_evidence. It is categorised as a Read tool in the RobotWS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RobotWS MCP Server MCP server in PolicyLayer and add a rule for search_evidence: 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 RobotWS MCP Server. Nothing to install.
search_evidence 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 search_evidence 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 search_evidence. 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.
search_evidence is provided by the RobotWS MCP Server MCP server (stella555359/robotws_mcp_server). 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 →