Generate the Project Playbook / Architecture Decision Record (ARD). Aggregates ALL pipeline outputs - research, PRD, design decisions, architecture, implementation plan, quality/security findings, traceability matrix - into a single comprehensive markdown document. This is the master deliverable ...
AI agents use playbook_generate to create or update resources in RC Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RC Engine environment.
This tool creates and writes a new deliverable document by aggregating existing pipeline outputs. While the generation is automated and non-destructive, it produces a new artifact and persists it to the filesystem. The severity is medium because the document is informational/architectural rather than critical system data, and the write operation is reversible—the file can be deleted or regenerated.
From the tool's definition Tool creates a new comprehensive markdown document saved to rc-method/PLAYBOOK-{name}.md. Described as 'generates' and 'saves to' a file, indicating file creation/writing.
Attacks that exploit this kind of access
Generate the Project Playbook / Architecture Decision Record (ARD). Aggregates ALL pipeline outputs - research, PRD, design decisions, architecture, implementation plan, quality/security findings, traceability matrix - into a single comprehensive markdown document. This is the master deliverable that a non-technical user can hand to a development team. Saves to rc-method/PLAYBOOK-{name}.md. Requires at least one pipeline phase to have been completed. It is categorised as a Write tool in the RC Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RC Engine MCP server in PolicyLayer and add a rule for playbook_generate: 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 RC Engine. Nothing to install.
playbook_generate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the playbook_generate 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_generate. 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_generate is provided by the RC Engine MCP server (originalrashmi/rc-engine-product-framework). 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 →