Search conversations by machine, hostname, or platform
AI agents call search_by_machine to retrieve information from Claude Code History MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical conversation metadata filtered by machine/hostname/platform. It performs no writes, deletions, code execution, or financial operations. The blast radius of misuse is minimal—an AI agent could retrieve conversation history it shouldn't access, but cannot alter or delete it. Classified as Read with low severity.
From the tool's definition Tool description states 'Search conversations by machine, hostname, or platform' — a query operation with no modification or side effects. Sibling tools include 'search', 'get_conversation', 'list_projects', all retrieval-only operations.
Attacks that exploit this kind of access
Search conversations by machine, hostname, or platform. It is categorised as a Read tool in the Claude Code History MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Code History MCP server in PolicyLayer and add a rule for search_by_machine: 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 Claude Code History MCP. Nothing to install.
search_by_machine 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_machine 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_machine. 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_machine is provided by the Claude Code History MCP server (tim0120/claude-code-history-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 →