Surface unfinished work — user turns from the last 14 days ending in a
AI agents call bob_open_threads to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool surfaces/lists unfinished work items from recent conversation history, which is a read/query operation. The description appears truncated ('ending in a') but the core action is retrieving data. No modification, execution, or destructive behavior is indicated. Confidence is slightly reduced due to the truncated description.
From the tool's definition 'Surface unfinished work — user turns from the last 14 days' — retrieves/queries conversation history data with no apparent side effects
Documented attack patterns abuse exactly the kind of access bob_open_threads 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 bob_open_threads:
{
"version": "1",
"default": "deny",
"tools": {
"bob_open_threads": {}
}
}bob_open_threads 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.
Surface unfinished work — user turns from the last 14 days ending in a. It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for bob_open_threads: 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.
bob_open_threads 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 bob_open_threads 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 bob_open_threads. 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.
bob_open_threads is provided by the Brain MCP server (mordechaipotash/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.
34 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.