Reconstruct work-in-progress on a domain/topic. Returns the most recent
AI agents call bob_tunnel_state 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.
This tool retrieves and returns historical context and cognitive state information. The words 'reconstruct' and 'returns' indicate a Read operation that queries stored conversation embeddings and prior work state. There is no indication of side effects, code execution, data modification, or irreversible actions. The severe category (Financial/Destructive/Execute) do not apply.
From the tool's definition Tool description indicates it 'Reconstruct[s] work-in-progress on a domain/topic. Returns the most recent' — a retrieval operation that queries indexed conversation history and cognitive state without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access bob_tunnel_state 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_tunnel_state:
{
"version": "1",
"default": "deny",
"tools": {
"bob_tunnel_state": {}
}
} bob_tunnel_state 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.
Reconstruct work-in-progress on a domain/topic. Returns the most recent. 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_tunnel_state: 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_tunnel_state 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_tunnel_state 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_tunnel_state. 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_tunnel_state 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.