Search through Claude Code conversation history, .claude files (rules, skills, agents, plans, CLAUDE.md), memories, and task management data with smart insights
AI agents call search to retrieve information from Claude Historian 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 historical data from conversations and files. It has no side effects—it does not modify, delete, or execute anything. The search operation is a pure read operation that returns information to help users find past solutions and context.
From the tool's definition Tool description states it 'Search through Claude Code conversation history' and lists reading from files and memories. The verb 'search' and context of querying past conversation data indicate retrieval without modification.
Documented attack patterns abuse exactly the kind of access search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Historian, and nothing reaches the server without passing your rules. This is the rule we recommend for search:
{
"version": "1",
"default": "deny",
"tools": {
"search": {}
}
}search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search through Claude Code conversation history, .claude files (rules, skills, agents, plans, CLAUDE.md), memories, and task management data with smart insights. It is categorised as a Read tool in the Claude Historian MCP Server, which means it retrieves data without modifying state.
Register the Claude Historian MCP server in PolicyLayer and add a rule for search: 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 Historian. Nothing to install.
search 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 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. 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 is provided by the Claude Historian MCP server (vvkmnn/claude-historian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Claude Historian tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Claude Historian tools catalogued and risk-classified — across an index of 42,500+ MCP servers.