save_conversation_tool
AI agents use save_conversation_tool to create or update resources in Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Brain environment.
Based on the name and server context, this tool most likely creates or modifies persistent data (saving conversations as notes). This is a Write operation—reversible and non-destructive. Severity is medium because misuse could create unwanted records, but data remains editable/deletable. Confidence is lowered due to missing description.
From the tool's definition Tool name 'save_conversation_tool' indicates it persists conversation data. Server context shows a note-taking system with write tools (append_to_note_tool, create_note_tool). No description provided to clarify exact behavior.
Documented attack patterns abuse exactly the kind of access save_conversation_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Brain, and nothing reaches the server without passing your rules. This is the rule we recommend for save_conversation_tool:
{
"version": "1",
"default": "deny",
"tools": {
"save_conversation_tool": {
"limits": [
{
"counter": "save_conversation_tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_conversation_tool 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.
save_conversation_tool. It is categorised as a Write tool in the Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Brain MCP server in PolicyLayer and add a rule for save_conversation_tool: 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 Brain. Nothing to install.
save_conversation_tool 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 save_conversation_tool 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 save_conversation_tool. 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.
save_conversation_tool is provided by the Brain MCP server (irahulstomar/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Brain, 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.
10 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.