crew

Run a role-based pipeline (default Researcher→Writer→Reviewer), each role on its own provider, passing output down the chain. Use for role-specialized teamwork; use run_workflow for plain sequential tasks.

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

What crew does on Proxima

AI agents invoke crew 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 crew needs a policy

The 'crew' tool orchestrates execution of code generation, analysis, and writing tasks across multiple external AI providers in a defined workflow. While individual AI queries are typically Read operations, this tool *runs* a complex multi-stage pipeline whose behavior is determined by user-supplied arguments (the task, role definitions, and prompts).

From the tool's definition Tool description states it 'Run[s] a role-based pipeline' with multiple AI providers in sequence, 'passing output down the chain.' This involves executing external operations (calls to ChatGPT, Claude, Gemini, Perplexity) whose effects depend on the…

Questions about crew

What does the crew tool do? +

Run a role-based pipeline (default Researcher→Writer→Reviewer), each role on its own provider, passing output down the chain. Use for role-specialized teamwork; use run_workflow for plain sequential tasks. 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 crew? +

Register the Proxima MCP server in PolicyLayer and add a rule for crew: 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 crew? +

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

Can I rate-limit crew? +

Yes. Add a rate_limit block to the crew 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 crew completely? +

Set action: deny in the PolicyLayer policy for crew. 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 crew? +

crew 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

crew 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.