General document directory (warranties, manuals, contracts, IDs, titles, insurance policies, legal docs). Search by name/category/subject, list expiring soon, add or update.
AI agents use documents 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.
The tool supports both read operations (search, list expiring soon) and write operations (add or update). Per the rules, the most severe applicable category is chosen. The ability to add or update highly sensitive personal documents (IDs, legal docs, insurance policies, contracts, titles) makes this a Write tool with high severity, as an AI agent misusing it could tamper with, corrupt, or insert false sensitive…
From the tool's definition 'add or update' alongside storing sensitive document types: 'warranties, manuals, contracts, IDs, titles, insurance policies, legal docs'
Attacks that exploit this kind of access
General document directory (warranties, manuals, contracts, IDs, titles, insurance policies, legal docs). Search by name/category/subject, list expiring soon, add or update. 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 documents: 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.
documents 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 documents 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 documents. 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.
documents 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 →