search_sessions
AI agents call search_sessions 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 retrieves and queries local GitHub Copilot conversation history data without modifying, deleting, or executing anything. Even though the description is empty, the context from the server description and sibling tool names clearly indicates a search/query operation on stored data, which is the definition of a Read category tool. No side effects or data modification occurs.
From the tool's definition Tool name 'search_sessions' combined with server description stating it 'Enables searching and analyzing GitHub Copilot's conversation history' and provides 'full-text search' capabilities.
Attacks that exploit this kind of access
search_sessions. 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_sessions: 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_sessions 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_sessions 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_sessions. 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_sessions 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 →