agent_fleet_run

SERVERYaver SOURCEyaver-cli

High RISK CLASS

Category Execute

Parameters 101 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/agent-fleet-run.md

WHAT IT DOES

What agent_fleet_run does on Yaver

AI agents invoke agent_fleet_run to trigger actions in Yaver. 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.

Parameter	Type	Required	Description
`name`	string	—	Optional run name.
`prompt`	string	Yes	The coding goal.
`work_dir`	string	—	Absolute repository path; defaults to the agent work directory.
`master_model`	string	—	Optional premium master model.
`max_parallel`	integer	—	Concurrency ceiling; this dependent workflow normally runs sequentially.
`worker_model`	string	—	Optional worker model such as deepseek/deepseek-flash.
`master_runner`	string	—	Premium planner/reviewer runner; empty uses master preference.
`worker_runner`	string	—	Worker runner; defaults to opencode.
`allowed_devices`	array	—	Optional machine pool. Include one device to run both roles on that computer.
`preferred_device`	string	—	Optional preferred device; same-device master/worker is supported.

Parameters from the server's own tool schema.

RISK

Why agent_fleet_run is rated High

Inspects code repositories and executes automated coding tasks with independent validation loops.

From the tool's definition Run Yaver's opinionated master/worker coding loop: master inspects repository and writes architecture.

Risk signalsHigh parameter count (10 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs agent_fleet_run safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_fleet_run, this is the rule to start with:

agent_fleet_run Rate-limited

agent_fleet_run stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent_fleet_run": {
      "limits": [
        {
          "counter": "agent_fleet_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every agent_fleet_run call is checked against it from then on.

FAQ

Questions about agent_fleet_run

What does the agent_fleet_run tool do? +

Run Yaver's opinionated master/worker coding loop: the master inspects the repository and writes architecture, roadmap, risks, and testing strategy; an OpenCode worker implements, iterates tests, and emits a structured report; the master independently validates the diff and report. Master and worker may be separate machines or separate runner processes on the same computer. OpenCode is the default worker runner. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does agent_fleet_run accept? +

agent_fleet_run accepts 10 parameters: name, prompt, work_dir, master_model, max_parallel, worker_model, master_runner, worker_runner, allowed_devices, preferred_device. Required: prompt. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on agent_fleet_run? +

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

What risk level is agent_fleet_run? +

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

Can I rate-limit agent_fleet_run? +

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

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

agent_fleet_run is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 678 Yaver tools → High-risk tools on this server →

Across the catalogue

editor_run_template on 010 Editor →run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →