Traverse the relation graph from a thought. Backward = what led here. Forward = what followed. Returns ordered chain with relation types.
AI agents call atelier_trace to retrieve information from Mybrain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
atelier_trace retrieves and queries the semantic relation graph to show causal chains (backward/forward links between thoughts). It has no side effects—it does not create, modify, delete, or execute operations. This is pure data retrieval, fitting the Read category (retrieval/querying data with no side effects).
From the tool's definition Tool description states it 'Traverse[s] the relation graph from a thought' and 'Returns ordered chain with relation types.' The verb 'traverse' and 'returns' indicate read-only graph traversal with no data modification, deletion, or external execution.
Documented attack patterns abuse exactly the kind of access atelier_trace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mybrain, and nothing reaches the server without passing your rules. This is the rule we recommend for atelier_trace:
{
"version": "1",
"default": "deny",
"tools": {
"atelier_trace": {}
}
}atelier_trace 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.
Traverse the relation graph from a thought. Backward = what led here. Forward = what followed. Returns ordered chain with relation types. It is categorised as a Read tool in the Mybrain MCP Server, which means it retrieves data without modifying state.
Register the Mybrain MCP server in PolicyLayer and add a rule for atelier_trace: 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 Mybrain. Nothing to install.
atelier_trace 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 atelier_trace 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 atelier_trace. 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.
atelier_trace is provided by the Mybrain MCP server (robertsfeir/mybrain). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mybrain, 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.
8 Mybrain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.