Get the full conversation tree (DAG) for a conversation.
AI agents call conversation_tree to retrieve information from Rekal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries structural data about conversations (a directed acyclic graph) without side effects. It performs a read-only lookup of existing conversation history and relationships. No data is created, modified, deleted, or executed. The blast radius is minimal—an agent querying conversation history poses no risk of data loss, unauthorized modification, or external harm.
From the tool's definition Tool name 'conversation_tree' and description 'Get the full conversation tree' indicate a retrieval operation with no modification or deletion of data.
Documented attack patterns abuse exactly the kind of access conversation_tree gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rekal, and nothing reaches the server without passing your rules. This is the rule we recommend for conversation_tree:
{
"version": "1",
"default": "deny",
"tools": {
"conversation_tree": {}
}
}conversation_tree 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 tree (DAG) for a conversation. It is categorised as a Read tool in the Rekal MCP Server, which means it retrieves data without modifying state.
Register the Rekal MCP server in PolicyLayer and add a rule for conversation_tree: 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 Rekal. Nothing to install.
conversation_tree 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 conversation_tree 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 conversation_tree. 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.
conversation_tree is provided by the Rekal MCP server (janbjorge/rekal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rekal, 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.
21 Rekal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.