publish_ci_dispatch · Yaver MCP: Risk & Policy

WHAT IT DOES

What publish_ci_dispatch does on Yaver

AI agents use publish_ci_dispatch 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
`dir`	string	—	Project directory. Defaults to the agent work dir.
`target`	string	—	Target ID from .yaver/publish.yaml. Defaults to defaultTarget.
`allow_github_fallback`	boolean	—	Allow explicit GitHub workflow_dispatch fallback if the target/project permits it.

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why publish_ci_dispatch needs a policy

An AI agent can call publish_ci_dispatch 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.

Risk signalsAccepts file system path (dir)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

publish_ci_dispatch Rate-limited

publish_ci_dispatch 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": {
    "publish_ci_dispatch": {
      "limits": [
        {
          "counter": "publish_ci_dispatch_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 publish_ci_dispatch

What does the publish_ci_dispatch tool do? +

Alias of publish_run for CI-oriented clients. Use allow_github_fallback=true when you want GitHub dispatch as the fallback path after Yaver/local execution fails. 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 publish_ci_dispatch accept? +

publish_ci_dispatch accepts 3 parameters: dir, target, allow_github_fallback. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on publish_ci_dispatch? +

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

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

Can I rate-limit publish_ci_dispatch? +

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

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

publish_ci_dispatch 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.