runner_auth_set · Yaver MCP: Risk & Policy

WHAT IT DOES

What runner_auth_set does on Yaver

AI agents use runner_auth_set to create or update resources in Yaver — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yaver environment.

PARAMETERS

Parameter	Type	Required	Description
`notes`	string	—
`runner`	string	Yes
`device_id`	string	—	Optional remote device ID
`glm_api_key`	string	—
`zai_api_key`	string	—
`openai_api_key`	string	—
`anthropic_api_key`	string	—
`anthropic_auth_token`	string	—
`claude_code_oauth_token`	string	—

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why runner_auth_set needs a policy

An AI agent can call runner_auth_set faster than any human can review — one bad instruction and it creates or modifies resources in Yaver by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runner_auth_set Rate-limited

runner_auth_set stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "runner_auth_set": {
      "limits": [
        {
          "counter": "runner_auth_set_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yaver, so you can run agents against it safely.

FAQ

Questions about runner_auth_set

What does the runner_auth_set tool do? +

Save runner/provider auth into the local or remote Yaver vault for headless setup. Supports claude, codex, opencode, and glm. Optional device_id writes to another owned Yaver machine. It is categorised as a Write tool in the Yaver MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does runner_auth_set accept? +

runner_auth_set accepts 9 parameters: notes, runner, device_id, glm_api_key, zai_api_key, openai_api_key, anthropic_api_key, anthropic_auth_token, claude_code_oauth_token. Required: runner. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on runner_auth_set? +

Register the Yaver MCP server in PolicyLayer and add a rule for runner_auth_set: 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 runner_auth_set? +

runner_auth_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit runner_auth_set? +

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

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

runner_auth_set 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.