Phase 6 (Forge). Call once per task from the approved task list. Loads the PRD, architecture, and task context, then generates implementation guidance for the specified task_id (e.g.,
AI agents call rc_forge_task to retrieve information from RC Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool loads existing artifacts (PRD, architecture, task context) and generates implementation guidance. There is no indication it writes, executes, or modifies any data — it produces textual guidance for a human or agent to act upon. Confidence is moderate because the description is truncated and 'Forge' implies building/executing, but the described behavior is read-and-generate.
From the tool's definition 'Loads the PRD, architecture, and task context, then generates implementation guidance for the specified task_id' — the tool reads existing documents and produces guidance output
Attacks that exploit this kind of access
Phase 6 (Forge). Call once per task from the approved task list. Loads the PRD, architecture, and task context, then generates implementation guidance for the specified task_id (e.g.,. It is categorised as a Read tool in the RC Engine MCP Server, which means it retrieves data without modifying state.
Register the RC Engine MCP server in PolicyLayer and add a rule for rc_forge_task: 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.
rc_forge_task 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 rc_forge_task 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 rc_forge_task. 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.
rc_forge_task 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 →