New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

mobile_project_build

Start the project's dev server if needed and build the Hermes bundle that Yaver loads on the phone. Works locally or on an owned remote Yaver device. This is the MCP path for a contributor on WSL/Linux/macOS to prepare a fresh Expo / React Native clone for real iPhone/Android testing without Test...

SERVERYaver SOURCEyaver-cli
High RISK CLASS
Category Execute
Parameters 40 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/mobile-project-build.md

What mobile_project_build does on Yaver

AI agents invoke mobile_project_build 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.

ParameterTypeRequiredDescription
platform string Target platform (default: ios)
device_id string Optional owned Yaver device id/name/alias to build on.
directory string Project directory (default: agent work dir)
framework string Optional framework override (expo or react-native)

Parameters from the server's own tool schema.

Why mobile_project_build is rated High

This tool runs build and server processes on local or remote machines, which constitutes code execution. While the tool itself is designed for legitimate development workflows, an AI agent with access could maliciously trigger builds with altered project files, execute arbitrary code through the dev server, or compromise a remote Yaver device. The blast radius extends to device loading and app deployment.

From the tool's definition Tool description explicitly states it 'Start[s] the project's dev server' and 'build[s] the Hermes bundle that Yaver loads on the phone.' These are operations that execute code (dev server startup, Hermes bundle compilation) and trigger external processes…

Risk signalsAccepts file system path (directory)

Questions about mobile_project_build

What does the mobile_project_build tool do? +

Start the project's dev server if needed and build the Hermes bundle that Yaver loads on the phone. Works locally or on an owned remote Yaver device. This is the MCP path for a contributor on WSL/Linux/macOS to prepare a fresh Expo / React Native clone for real iPhone/Android testing without TestFlight. 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 mobile_project_build accept? +

mobile_project_build accepts 4 parameters: platform, device_id, directory, framework. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on mobile_project_build? +

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

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

Can I rate-limit mobile_project_build? +

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

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

mobile_project_build 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.

More on Yaver, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Yaver's. Pull the full record:

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.