your reading list (books, articles, papers). Get filtered list, add new items, update status, or rate finished items.
AI agents call reading_list 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.
Although the tool permits adding and updating items (which might nominally qualify as Write), the context is a personal reading list with no external side effects or irreversible consequences. The dominant capability is retrieval ('Get filtered list'), and updates are trivial metadata changes (status, ratings) on personal data with zero blast radius if misused by an AI agent.
From the tool's definition Tool description states: 'Get filtered list, add new items, update status, or rate finished items.' The primary operations (get, filter, add, update, rate) are all data retrieval and reversible modification of a personal reading list.
Attacks that exploit this kind of access
your reading list (books, articles, papers). Get filtered list, add new items, update status, or rate finished items. 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 reading_list: 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.
reading_list 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 reading_list 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 reading_list. 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.
reading_list 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 →