Skip to main content
Glama
michaelneale

Goose App Maker MCP

by michaelneale

app_open

Opens a Goose web application in your default browser, automatically serving it first if needed. Use this tool to launch and access your created apps directly.

Instructions

Open an app in the default web browser. If the app is not currently being served,
it will be served first.
Can only open one app at a time.

Args:
    app_name: Name of the application to open

Returns:
    A dictionary containing the result of the operation

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
app_nameYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • main.py:515-581 (handler)
    The core handler function implementing the app_open tool. It serves the app if not running, then opens it in the default browser (preferring Chrome app mode on macOS).
    def app_open(app_name: str) -> Dict[str, Any]:
        """
        Open an app in the default web browser. If the app is not currently being served,
        it will be served first.
        Can only open one app at a time.
        
        Args:
            app_name: Name of the application to open
        
        Returns:
            A dictionary containing the result of the operation
        """
        global http_server
        
        try:
            # Find the app directory
            app_path = os.path.join(APP_DIR, app_name)
            if not os.path.exists(app_path):
                return {
                    "success": False, 
                    "error": f"App '{app_name}' not found at {app_path}"
                }
            
            # If the server is not running, start it
            if not http_server:
                serve_result = app_serve(app_name)
                if not serve_result["success"]:
                    return serve_result
                # Get the URL from the serve result
                url = serve_result["url"]
            else:
                # Use the current server port
                url = f"http://localhost:{server_port}"
            
            # Check if we're on macOS
            if os.uname().sysname == "Darwin":  # macOS
                # Use Chrome in app mode
                chrome_path = "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
                if os.path.exists(chrome_path):
                    logger.info(f"Opening app in Chrome app mode: {url}")
                    # Use Popen instead of run to avoid blocking
                    subprocess.Popen([chrome_path, f"--app={url}"], 
                                     stdout=subprocess.DEVNULL, 
                                     stderr=subprocess.DEVNULL)
                else:
                    # Fallback to default browser if Chrome is not installed
                    logger.info(f"Chrome not found, opening in default browser: {url}")
                    # Use Popen instead of run to avoid blocking
                    subprocess.Popen(["open", url], 
                                     stdout=subprocess.DEVNULL, 
                                     stderr=subprocess.DEVNULL)
            else:
                # For non-macOS systems, use the default browser
                # Use Popen instead of run to avoid blocking
                subprocess.Popen(["open", url], 
                                 stdout=subprocess.DEVNULL, 
                                 stderr=subprocess.DEVNULL)
            
            return {
                "success": True,
                "app_name": app_name,
                "url": url,
                "message": f"App '{app_name}' opened in browser at {url}"
            }
        except Exception as e:
            logger.error(f"Error opening app: {e}")
            return {"success": False, "error": f"Failed to open app: {str(e)}"}
  • main.py:514-514 (registration)
    MCP decorator that registers the app_open function as a tool.
    @mcp.tool()
  • Function signature and docstring defining the input schema (app_name: str) and output (Dict[str, Any]).
    def app_open(app_name: str) -> Dict[str, Any]:
        """
        Open an app in the default web browser. If the app is not currently being served,
        it will be served first.
        Can only open one app at a time.
        
        Args:
            app_name: Name of the application to open
        
        Returns:
            A dictionary containing the result of the operation
        """
  • Documentation reference to the app_open tool in the system instructions.
    app_open - open an app in a browser (macos)
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it opens in a web browser, serves the app if not already served, and enforces a single-app-at-a-time constraint. However, it lacks details on permissions, error handling, or what 'served first' entails (e.g., time, resources). This is adequate but has gaps for a mutation tool.

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?

The description is appropriately sized and front-loaded: the first sentence states the core action, followed by important behavioral notes and parameter/return details. Every sentence adds value without redundancy, and the structure with 'Args:' and 'Returns:' sections enhances clarity efficiently.

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?

Given the tool's moderate complexity (mutation with constraints), no annotations, and an output schema present (so return values are documented elsewhere), the description is fairly complete. It covers purpose, key behavior, and parameter semantics, but could improve by addressing error cases or interaction with sibling tools like app_serve. The presence of an output schema reduces the need for return value details.

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

Parameters4/5

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

The schema description coverage is 0%, so the description must compensate. It adds meaning by explaining 'app_name' as 'Name of the application to open,' which clarifies the parameter's role beyond the schema's basic type. Since there's only one parameter, this is sufficient to understand its use, though it doesn't specify format or constraints like valid app names.

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?

The description clearly states the verb ('Open') and resource ('an app in the default web browser'), making the purpose specific and understandable. It distinguishes from siblings like app_serve (which only serves) and app_list (which lists), though it doesn't explicitly name alternatives. The mention of serving if needed adds useful context but doesn't fully differentiate from app_serve in a comparative way.

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?

The description implies usage by stating 'Can only open one app at a time,' which provides some context on limitations, but it doesn't explicitly say when to use this tool versus alternatives like app_serve or app_list. No guidance on prerequisites or exclusions is given, leaving the agent to infer based on the description alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/michaelneale/goose-app-maker-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server