Phase 6 (Forge) BATCH MODE. Builds ALL pending tasks from the approved task list in one call, respecting dependency order. Equivalent to calling rc_forge_task for each task sequentially. If a task fails, it is recorded as failed and the next task continues. Returns a summary of all tasks with suc...
AI agents invoke rc_forge_all to trigger actions in RC Engine. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a batch build process across all pending tasks, triggering external operations (code/artifact generation) whose effects depend on the task list contents. It's a broad-scope execution tool that could generate significant amounts of code or artifacts in one call, giving it a high blast radius if misused. It is not purely destructive but runs automated build operations with cascading effects.
From the tool's definition Builds ALL pending tasks from the approved task list in one call... Equivalent to calling rc_forge_task for each task sequentially... If a task fails, it is recorded as failed and the next task continues.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Phase 6 (Forge) BATCH MODE. Builds ALL pending tasks from the approved task list in one call, respecting dependency order. Equivalent to calling rc_forge_task for each task sequentially. If a task fails, it is recorded as failed and the next task continues. Returns a summary of all tasks with success/failure status. Prerequisites: Phase 5 gate approved, task list must exist in rc-method/tasks/. After completion: proceed to rc_gate to approve Phase 6, then rc_connect for integration check. It is categorised as a Execute tool in the RC Engine MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RC Engine MCP server in PolicyLayer and add a rule for rc_forge_all: 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_all is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the rc_forge_all 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_all. 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_all 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 →