User Layer-4 semantic facts (subject-predicate-object). Search by similarity, list by subject, add new facts, update or forget existing ones, or promote a memory entry into a fact.
AI agents use facts to create or update resources in Personal Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Personal Brain environment.
While the tool includes read operations (search by similarity, list by subject), the presence of write capabilities (add, update, forget) makes this a Write tool. The 'forget' operation could be considered destructive, but the phrasing suggests logical deletion or unmarking rather than irreversible destruction, and the description emphasizes reversibility through the ability to update or modify.
From the tool's definition Tool description explicitly states capability to 'add new facts, update or forget existing ones', which are reversible write operations on stored data. The mention of 'promote a memory entry into a fact' further confirms data modification capability.
Attacks that exploit this kind of access
User Layer-4 semantic facts (subject-predicate-object). Search by similarity, list by subject, add new facts, update or forget existing ones, or promote a memory entry into a fact. It is categorised as a Write tool in the Personal Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Personal Brain MCP server in PolicyLayer and add a rule for facts: 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 Personal Brain. Nothing to install.
facts 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 facts 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 facts. 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.
facts is provided by the Personal Brain MCP server (phantomts/personal-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 →