OpenMouse MCP

Open a URL directly in a browser

browser_open

Idempotent

Opens a known http:// or https:// URL directly in the default browser, Edge, or Chrome, or navigates an embedded Playwright browser in cloud mode, skipping screenshots and mouse movement.

Instructions

Fast path for opening a known http:// or https:// URL. On Windows this launches the default browser, Edge, or Chrome directly without screenshots or mouse movement. In cloud mode it navigates the embedded Playwright browser and blocks private addresses by default.

Input Schema

Name	Required	Description	Default
`url`	Yes	Absolute http:// or https:// URL.
`browser`	No		default

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.0.2Oct 25, 2026

addedInput schema / properties / browser

Added value: +{
+  "default": "default",
+  "enum": [
+    "default",
+    "edge",
+    "chrome"
+  ],
+  "title": "Browser",
+  "type": "string"
+}

First observedv1.0.0Oct 24, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare openWorldHint/idempotentHint/readOnlyHint, but the description adds real value beyond them: platform-specific launch behavior (default browser, Edge, Chrome on Windows) and the fact that cloud mode uses an embedded Playwright browser that blocks private addresses by default. It does not cover failure/timeout behavior or whether navigation waits for load.

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?

Three short sentences, each carrying distinct information (purpose/scope, Windows routing, cloud-mode behavior), with the fast-path framing front-loaded. No filler.

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 an output schema present, return values needn't be explained, and the description covers the key differentiators of platform and cloud mode. Minor gap: no note on what happens with the browser parameter off Windows or on failure.

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 50%: url is documented in-schema, while browser has only an enum with no description. The description partially compensates by mapping the browser choice ("default browser, Edge, or Chrome"), but only in the Windows context — it never says what browser does in cloud/Playwright mode, so the gap is only half closed.

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?

Opening a known absolute http(s) URL is stated as a specific verb+resource, and "Fast path" plus "without screenshots or mouse movement" implicitly separates it from the computer_observe/mouse_screenshot loop. It stops short of naming a sibling tool outright, which keeps it out of the top band.

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

Usage Guidelines3/5

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

"Known http:// or https:// URL" is a usable precondition and "fast path" implies direct navigation over screenshot-driven interaction. However, it never states when NOT to use this (e.g., when the page needs to be inspected or clicked, use computer_observe/mouse_click) and names no alternative.

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

Deploy Server