Search through conversation history by content (useful for finding specific topics across all conversations)
AI agents call search_conversations to retrieve information from Claude Code History 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 conversation data without any side effects. It matches the 'Read' category definition as it searches and filters existing data. Severity is medium because conversation history may contain sensitive information (API keys, personal data, business logic details) that could be exposed through search results, but the tool itself only reads without modifying or deleting data.
From the tool's definition Tool description states it searches through conversation history by content and finds specific topics across conversations.
Documented attack patterns abuse exactly the kind of access search_conversations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code History MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_conversations:
{
"version": "1",
"default": "deny",
"tools": {
"search_conversations": {}
}
}search_conversations 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 conversation history by content (useful for finding specific topics across all conversations). It is categorised as a Read tool in the Claude Code History MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Claude Code History MCP Server MCP server in PolicyLayer and add a rule for search_conversations: 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 Server. Nothing to install.
search_conversations 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_conversations 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_conversations. 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_conversations is provided by the Claude Code History MCP Server MCP server (yudppp/claude-code-history-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code History MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Claude Code History MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.