AI agents call search_playbook to retrieve information from SIFTGuard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static or semi-static investigation guidance documents keyed by threat category (ransomware, malware, intrusion, lateral_movement). It has no side effects, does not execute code, does not modify data, and does not access sensitive evidence directly—it merely fetches reference material. This is a pure Read operation with minimal blast radius even if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Retrieve DFIR investigation playbook' — a lookup/query operation that retrieves pre-existing documentation for a specified threat type without modifying systems or data.
Attacks that exploit this kind of access
Retrieve DFIR investigation playbook for a threat type: ransomware | malware | intrusion | lateral_movement. It is categorised as a Read tool in the SIFTGuard MCP Server, which means it retrieves data without modifying state.
Register the SIFTGuard MCP server in PolicyLayer and add a rule for search_playbook: 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 SIFTGuard. Nothing to install.
search_playbook 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 search_playbook 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 search_playbook. 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.
search_playbook is provided by the SIFTGuard MCP server (sodiq-code/siftguard). 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 →