Get the full conversation history for a session
AI agents call get_conversation_history to retrieve information from Pearl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves conversation history—a read-only operation with no side effects, no code execution, and no data modification. While the data returned might be sensitive depending on conversation content, the tool itself performs only a query/fetch operation. Severity is low because retrieval of conversation logs is a standard read operation with no destructive or executable capability.
From the tool's definition Tool name 'get_conversation_history' and description 'Get the full conversation history for a session' indicate retrieval of existing data without modification or execution.
Documented attack patterns abuse exactly the kind of access get_conversation_history gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pearl, and nothing reaches the server without passing your rules. This is the rule we recommend for get_conversation_history:
{
"version": "1",
"default": "deny",
"tools": {
"get_conversation_history": {}
}
}get_conversation_history 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.
Get the full conversation history for a session. It is categorised as a Read tool in the Pearl MCP Server, which means it retrieves data without modifying state.
Register the Pearl MCP server in PolicyLayer and add a rule for get_conversation_history: 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 Pearl. Nothing to install.
get_conversation_history 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 get_conversation_history 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 get_conversation_history. 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.
get_conversation_history is provided by the Pearl MCP server (pearl-com/pearl_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pearl, 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.
5 Pearl tools catalogued and risk-classified — across an index of 43,000+ MCP servers.