AI agents use conversation_start to create or update resources in Rekal — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rekal environment.
Based on the tool name 'conversation_start' and the server context (long-term memory via SQLite for LLMs), this tool likely initiates/creates a new conversation thread in the local storage. Creating a new record is a Write operation. Confidence is reduced due to the empty description.
From the tool's definition Tool name is 'conversation_start'; description is empty or uninformative.
Documented attack patterns abuse exactly the kind of access conversation_start 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_start:
{
"version": "1",
"default": "deny",
"tools": {
"conversation_start": {
"limits": [
{
"counter": "conversation_start_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}conversation_start stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
conversation_start. It is categorised as a Write tool in the Rekal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rekal MCP server in PolicyLayer and add a rule for conversation_start: 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_start is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the conversation_start 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_start. 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_start 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.