project_runtime_apply

SERVERYaver SOURCEyaver-cli

Medium RISK CLASS

Category Write

Parameters 120 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/project-runtime-apply.md

WHAT IT DOES

What project_runtime_apply does on Yaver

AI agents use project_runtime_apply 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.

Parameter	Type	Required
`env`	object	—
`auth`	string	—
`jobs`	array	—
`name`	string	—
`stack`	string	—
`dryRun`	boolean	—
`backend`	string	—
`domains`	array	—
`runtime`	object	—
`directory`	string	—
`phoneSlug`	string	—
`placement`	object	—

Parameters from the server's own tool schema.

RISK

Why project_runtime_apply is rated Medium

This tool modifies project configuration files (.yaver/project.yaml) and triggers manifest application and sandbox promotions. These are reversible write operations rather than destructive deletions, but the ability to merge provider updates and run promotions creates a significant blast radius if an AI agent applies unintended changes to runtime configurations or deploys to production sandboxes without…

From the tool's definition Tool description states it will 'Merge runtime/provider updates into .yaver/project.yaml' and 'run manifest apply', indicating it modifies configuration files and executes deployment/promotion operations.

Risk signalsAccepts file system path (directory) · Handles credentials or secrets (auth) · High parameter count (15 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs project_runtime_apply 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 project_runtime_apply, this is the rule to start with:

project_runtime_apply Rate-limited

project_runtime_apply 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": {
    "project_runtime_apply": {
      "limits": [
        {
          "counter": "project_runtime_apply_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about project_runtime_apply

What does the project_runtime_apply tool do? +

Merge runtime/provider updates into .yaver/project.yaml, optionally connect provider accounts, run manifest apply, and plan or run mobile sandbox promotions. Supports either a project directory or a phoneSlug for phone-first sandboxes. 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 project_runtime_apply accept? +

project_runtime_apply accepts 12 parameters: env, auth, jobs, name, stack, dryRun, backend, domains, runtime, directory, phoneSlug, placement. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on project_runtime_apply? +

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

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

Can I rate-limit project_runtime_apply? +

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

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

project_runtime_apply 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 645 Yaver tools →

Across the catalogue

create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →