android-mcp

Overview Schema Source Related Servers Discussions Admin

open_url

Launches a URL or deep link in a specified debug app on an Android device or emulator using an ACTION_VIEW intent, then optionally returns UI changes or a screenshot.

Instructions

Open a URL / deep link in an allowed dev app with an ACTION_VIEW intent.

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": {
      "url": "<url>",
      "package": "<package>"
    },
    "name": "open_url"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes
`serial`	No	adb serial; optional when exactly one device is connected
`observe`	No	What to return after the action: changes (default: only what changed since you last saw the screen, full tree on a new screen), ui (full tree), screenshot, both (tree + screenshot), none	changes
`package`	Yes	The dev app that should handle the link
`settle_ms`	No	Wait before observing

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

B3.4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the burden; it does disclose the delivery mechanism (ACTION_VIEW intent) and the 'allowed dev app' constraint, which is real behavioral context. It omits failure behavior for a disallowed package, whether the previous screen is replaced, and any permission prerequisites, which matters for a tool that mutates device UI state.

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?

One front-loaded sentence with the verb, resource, and mechanism, and zero filler. Nothing is repeated from schema or annotations.

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

Completeness4/5

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

With no annotations and no output schema, the description plus the rich observe parameter documentation covers how to call it and what to expect back. The remaining gap is error/whitelist behavior for the package argument, a modest omission rather than a blocking one.

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 coverage is 80%: url, package, observe, and settle_ms are all documented in the schema, and the description adds nothing parameter-specific beyond implying package must be an 'allowed dev app'. Serial is undocumented in both places. Baseline 3 applies since the schema does the heavy lifting.

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

Purpose4/5

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

States a specific verb ('Open') and resource (URL / deep link) plus the mechanism (ACTION_VIEW intent), so the effect is unambiguous. It does not distinguish itself from the near-neighbor sibling launch_app, which also starts things in an app, leaving that discrimination to the agent.

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

Usage Guidelines2/5

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

The word 'allowed' implies a package whitelist exists but never states how to check it (list_dev_apps is a sibling) or what happens for a disallowed package. No when-to-use vs launch_app or when-not guidance is given.

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