AI agents call batch_get to retrieve information from Pen without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
batch_get performs read-only queries on document nodes. It retrieves data without side effects, matching the Read category definition. The severity is low because misuse merely returns data; it cannot modify, delete, or execute code. The recommendation to call it before updates/deletes confirms it is a passive lookup tool.
From the tool's definition Tool description states 'Search and read nodes from the document' with no modification or deletion capability. It is explicitly designed as a lookup/retrieval function that precedes write or destructive operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search and read nodes from the document. ALWAYS call this first before update_node or delete_node to find the correct node IDs. It is categorised as a Read tool in the Pen MCP Server, which means it retrieves data without modifying state.
Register the Pen MCP server in PolicyLayer and add a rule for batch_get: 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 Pen. Nothing to install.
batch_get 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 batch_get 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 batch_get. 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.
batch_get is provided by the Pen MCP server (@zseven-w/pen-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 →