Replace an existing thought with an updated version, preserving history. Use this when the user corrects a fact, changes a decision, or updates any previously stored knowledge. The old thought is marked superseded and linked to its replacement.
AI agents use supersede_thought 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.
This tool modifies existing data by replacing a thought and marking the old one as superseded, but it explicitly preserves history and links old to new — making it reversible/traceable. It is a Write operation (update/replace), not Destructive since the old thought is retained. Misuse could corrupt stored knowledge/decisions but history is preserved, warranting medium severity.
From the tool's definition Replace an existing thought with an updated version, preserving history... The old thought is marked superseded and linked to its replacement.
Attacks that exploit this kind of access
Replace an existing thought with an updated version, preserving history. Use this when the user corrects a fact, changes a decision, or updates any previously stored knowledge. The old thought is marked superseded and linked to its replacement. 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 supersede_thought: 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.
supersede_thought 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 supersede_thought 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 supersede_thought. 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.
supersede_thought is provided by the Brain MCP server (markschaake/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →