search_by_file_path
AI agents call search_by_file_path to retrieve information from Mcp Copilotcli History without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves Copilot conversation history by file path. It reads/queries local data with no side effects on data modification or deletion. Although the description is empty, the name and server context make it clear this is a retrieval operation. The blast radius of misuse is limited to unauthorized access to conversation history, not data loss or code execution.
From the tool's definition Tool name 'search_by_file_path' and sibling tools like 'search_sessions', 'list_recent_sessions', 'get_session_conversation' and 'get_session_stats' all indicate query/retrieval operations.
Attacks that exploit this kind of access
search_by_file_path. It is categorised as a Read tool in the Mcp Copilotcli History MCP Server, which means it retrieves data without modifying state.
Register the Mcp Copilotcli History MCP server in PolicyLayer and add a rule for search_by_file_path: 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 Mcp Copilotcli History. Nothing to install.
search_by_file_path 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_by_file_path 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_by_file_path. 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_by_file_path is provided by the Mcp Copilotcli History MCP server (micromichaelie/mcp-copilotcli-history). 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 →