thinking_trajectory
AI agents call thinking_trajectory 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 appears to retrieve or analyze conversation history and idea progression—a read operation with no side effects. The empty description lowers confidence slightly, but the sibling tools (bob_search, bob_recent, bob_conversations_by_date) are clearly read-focused, and thinking_trajectory fits that pattern. Severity is low because accessing user's own conversation history poses minimal risk even if misused.
From the tool's definition Tool name 'thinking_trajectory' and server description 'track idea evolution' indicate retrieval of historical thinking patterns. No description provided, but context suggests querying indexed conversation embeddings.
Documented attack patterns abuse exactly the kind of access thinking_trajectory 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 thinking_trajectory:
{
"version": "1",
"default": "deny",
"tools": {
"thinking_trajectory": {}
}
}thinking_trajectory 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.
thinking_trajectory. 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 thinking_trajectory: 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.
thinking_trajectory 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 thinking_trajectory 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 thinking_trajectory. 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.
thinking_trajectory 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.