Read the full verbatim text of past conversation turns by session + turn index. The read counterpart to search_conversation, which only returns short snippets — use it to hydrate a turn you located, or to pull a range of recent turns. Set includeToolOutput to also get tool results (re-parses the ...
AI agents call read_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 tool retrieves historical conversation data by session and turn index. It performs a pure read operation with no side effects, data modification, or capability to alter state. The inclusion of optional 'includeToolOutput' flag to parse transcript data remains a retrieval-only operation. No write, execute, destructive, or financial operations are possible with this tool.
From the tool's definition Tool name is 'read_conversation' with verb 'read' and description states it 'Read the full verbatim text of past conversation turns' and serves as 'The read counterpart to search_conversation, which only returns short snippets — use it to hydrate a turn'.
Documented attack patterns abuse exactly the kind of access read_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 read_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"read_conversation": {}
}
}read_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.
Read the full verbatim text of past conversation turns by session + turn index. The read counterpart to search_conversation, which only returns short snippets — use it to hydrate a turn you located, or to pull a range of recent turns. Set includeToolOutput to also get tool results (re-parses the raw transcript). 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 read_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.
read_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 read_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 read_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.
read_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.