Search through raw Cursor agent transcript files by keyword. Complements semantic search_brain by allowing exact keyword matching across all work sessions. Returns matching excerpts with surrounding context.
AI agents call search_work_history to retrieve information from Open Brain 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 existing data (work history transcripts) without side effects. It is a read-only search function that returns excerpts. While it accesses potentially sensitive work history, the action itself is non-destructive retrieval. Severity is low because misuse would only expose data to the AI agent rather than cause irreversible harm, financial loss, or code execution.
From the tool's definition Tool performs 'Search through raw Cursor agent transcript files by keyword' and 'Returns matching excerpts with surrounding context' — purely retrieval operations with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search through raw Cursor agent transcript files by keyword. Complements semantic search_brain by allowing exact keyword matching across all work sessions. Returns matching excerpts with surrounding context. It is categorised as a Read tool in the Open Brain MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Open Brain MCP Server MCP server in PolicyLayer and add a rule for search_work_history: 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 Open Brain MCP Server. Nothing to install.
search_work_history 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_work_history 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_work_history. 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_work_history is provided by the Open Brain MCP Server MCP server (subwizzll/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 →