Find or log tax document locations by year and type. Tracks where each document lives (OneDrive path, file cabinet, etc.).
AI agents call tax_documents to retrieve information from Personal Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool functions as a directory/index for locating tax documents (reading metadata about their paths and storage locations). While tax documents are sensitive personal information, this tool does not expose the documents themselves, execute queries against them, modify them, or enable financial transactions.
From the tool's definition Tool description states it enables "Find or log tax document locations" - primarily retrieves metadata about document storage locations rather than accessing document contents, executing operations, or modifying sensitive data.
Attacks that exploit this kind of access
Find or log tax document locations by year and type. Tracks where each document lives (OneDrive path, file cabinet, etc.). It is categorised as a Read tool in the Personal Brain MCP Server, which means it retrieves data without modifying state.
Register the Personal Brain MCP server in PolicyLayer and add a rule for tax_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.
tax_documents 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 tax_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 tax_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.
tax_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 →