Read from the Playbook knowledge wiki. Use action=
AI agents call playbook_read to retrieve information from Quarterback without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from a knowledge wiki without creating, modifying, or deleting anything. It is a straightforward read operation with minimal risk—the only concern would be if the wiki contains sensitive information, but that would be an organizational data governance issue rather than a tool risk. Low severity due to read-only nature and bounded scope (knowledge wiki).
From the tool's definition Tool name 'playbook_read' explicitly indicates a read operation. Description states 'Read from the Playbook knowledge wiki' with no mention of modifications, deletions, or side effects.
Attacks that exploit this kind of access
Read from the Playbook knowledge wiki. Use action=. It is categorised as a Read tool in the Quarterback MCP Server, which means it retrieves data without modifying state.
Register the Quarterback MCP server in PolicyLayer and add a rule for playbook_read: 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 Quarterback. Nothing to install.
playbook_read 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 playbook_read 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 playbook_read. 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.
playbook_read is provided by the Quarterback MCP server (bobbyrgoldsmith/quarterback). 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 →