Search through conversation history. Finds past decisions, discussions, and tool outputs from current or previous sessions.
AI agents call search_conversation to retrieve information from Local Rag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/retrieval tool that does not create, modify, delete, or execute anything. It simply searches and returns historical conversation data. The only potential concern is information disclosure, but within a local RAG system serving AI agents, searching one's own conversation history is a standard read operation with minimal blast radius.
From the tool's definition Tool searches through conversation history to find 'past decisions, discussions, and tool outputs' — purely a retrieval operation with no modification, deletion, or execution of code.
Documented attack patterns abuse exactly the kind of access search_conversation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Local Rag, and nothing reaches the server without passing your rules. This is the rule we recommend for search_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"search_conversation": {}
}
}search_conversation 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. Finds past decisions, discussions, and tool outputs from current or previous sessions. It is categorised as a Read tool in the Local Rag MCP Server, which means it retrieves data without modifying state.
Register the Local Rag MCP server in PolicyLayer and add a rule for search_conversation: 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 Local Rag. Nothing to install.
search_conversation 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_conversation 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_conversation. 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_conversation is provided by the Local Rag MCP server (thewinci/mimirs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Local Rag, 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.
29 Local Rag tools catalogued and risk-classified — across an index of 43,000+ MCP servers.