Skip to main content
Glama

dev_start

Starts a VibeView device session for live app testing and makes it the default for other tool calls, using local Metro for React Native debug builds or standalone mode for release/CI/cloud builds.

Instructions

Start a VibeView session held by this MCP server, and use it as the default session for every other tool call until dev_stop. By default it is a React Native dev loop: a debug build that loads its JS from your local Metro. Pass standalone: true to run any build as it is (a release, CI or cloud build) with no Metro. In a Flutter, Capacitor or native (not React Native) project the session is standalone automatically. Returns once the session accepts commands (device up, app installed), with the device it got (model, OS, form factor, posture) — call ui_tree next.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "platform": "<platform>"
    },
    "name": "dev_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
appNoApp id to run (from list_apps or upload_app). Must be an app for the chosen platform. Defaults to vibeview.json config, else to the app build_id belongs to.
modelNoRun on this exact device model, e.g. "iPhone Duo" or "Pixel 9 Pro Fold" for a foldable (any model list_device_models marks form_factor "foldable"). Names come from list_device_models. Omit for a default phone (or TV on TV platforms).
build_idNoRun this uploaded build of the app (an id from list_builds). Without standalone it must be a debug build (kind "debug"); with standalone, or in a Flutter, Capacitor or native (not React Native) project, any build of the app works. Omitted: the newest debug build (preferring one of the local project's own app version over a newer one of another version), or with standalone the newest release build. Not for roku.
platformYesPlatform to run on.
metro_portNoLocal Metro port (default: 8081, or vibeview.json). Ignored with standalone.
session_idNoSession ID to target. Optional: falls back to the MCP-server-held dev_start session, then this project's `vibeview dev --detach` state, if either is available.
standaloneNoRun the build as it is, with no Metro and no tunnel: for release builds, builds with an embedded JS bundle, CI and cloud builds. Code changes do not hot-reload. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Only readOnlyHint=false is provided, so the description carries the behavioral load and does so well: it discloses that the call blocks until the device is up and the app is installed, what it returns (model, OS, form factor, posture), and that code changes will not hot-reload in standalone mode. The Metro dependency and its absence in standalone are concrete operating context beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and its session-scoping consequence, then default mode, then the standalone escape hatch, then the completion/return contract. Five dense sentences with no filler or restated title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter launcher with no output schema, the definition covers what the call does, how long it blocks, what it hands back, and the next step. An agent has everything needed to invoke it correctly on the first try without guessing about Metro or build kind.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including standalone, metro_port and session_id is already documented in the schema. The description reinforces standalone's meaning but adds no syntax, format or edge-case detail the schema lacks; baseline 3 is appropriate where the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Start a VibeView session held by this MCP server" gives a specific verb plus resource, and immediately scopes it (becomes the default session until dev_stop). The default React Native dev-loop behavior and the standalone variant are stated, so an agent can distinguish this from dev_stop/stop_session without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the ordering relationship with siblings explicitly: session applies to "every other tool call until dev_stop" and "call ui_tree next" after return. It also names the conditions that select the variant (standalone for release/CI/cloud builds, and automatic standalone in Flutter, Capacitor or native projects).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.