run_loop

Iterate ONE task: generate → another AI reviews → improve, until it converges or hits maxTurns. Use to refine a single output; use run_workflow for distinct sequential steps.

Server Proxima zen4-bit/proxima
Category Execute
Risk class High
Parameters 00 required

What run_loop does on Proxima

AI agents invoke run_loop to trigger actions in Proxima. 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.

Why run_loop needs a policy

This tool triggers repeated execution of AI operations in a loop with conditional termination (convergence or maxTurns). While it does not permanently delete data (not Destructive) or move money (not Financial), it performs autonomous iterative operations whose outcomes depend on arguments and model behavior.

From the tool's definition The tool 'run_loop' iterates a task through multiple AI models in a generate-review-improve cycle controlled by maxTurns parameter.

Questions about run_loop

What does the run_loop tool do? +

Iterate ONE task: generate → another AI reviews → improve, until it converges or hits maxTurns. Use to refine a single output; use run_workflow for distinct sequential steps. It is categorised as a Execute tool in the Proxima MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_loop? +

Register the Proxima MCP server in PolicyLayer and add a rule for run_loop: 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 Proxima. Nothing to install.

What risk level is run_loop? +

run_loop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_loop? +

Yes. Add a rate_limit block to the run_loop 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.

How do I block run_loop completely? +

Set action: deny in the PolicyLayer policy for run_loop. 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.

What MCP server provides run_loop? +

run_loop is provided by the Proxima MCP server (zen4-bit/proxima). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

run_loop is one line of Proxima's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.