Skip to main content
Glama
yimajo

mcp-server-chatgpt-mac-app

by yimajo
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

mcp-server-chatgpt-mac-app

This is an MCP server that allows you to use the ChatGPT macOS app via MCP. The original version was written in Python as mcp-server-chatgpt-app, and this project is a TypeScript implementation of it.

Prerequisite

Related MCP server: mcp-server-chatgpt-app

Using npx

The MCP server can be used via npx, and you can choose to use it either globally on your macOS system or within any local project.

Global Usage

If you want to use it globally, run the following command in your CLI.

claude mcp add chatGPTOnMac -s user \
  -- npx mcp-server-chatgpt-mac-app

Local Project Usage

If you want to use it in any local directory, add the following to your .mcp.json.

{
  "mcpServers": {
    "chatGPTOnMac": {
      "command": "npx",
      "args": ["mcp-server-chatgpt-mac-app"],
      "cwd": ".",
      "env": {}
    }
  }
}

How to check if the MCP server has been added

To verify that the MCP server has been added, run the following command:

claude mcp list

If the output looks like the following, everything is set up correctly.

$ claude mcp list
chatGPTOnMac: npx mcp-server-chatgpt-mac-app

Local Development

If you want to improve this project locally.

build

git clone https://github.com/yimajo/mcp-server-chatgpt-mac-app.git
cd mcp-server-chatgpt-mac-app
pnpm install
pnpm build

Available Tools

1 tool
ask_via_shortcuts_cliD

An AI agent that utilizes the ChatGPT app for macOS.

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesSend to ChatGPT

TDQS

D1.9/5.0
Behavior1/5

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

With no annotations and only a minimal description, the tool's behavior is completely opaque. It does not disclose side effects, prerequisites (e.g., requires ChatGPT app), or what the return format is. The description provides no behavioral insight.

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

Conciseness2/5

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

The description is extremely short (9 words) but fails to convey useful information. It prioritizes brevity over substance, making it under-specified rather than concise.

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

Completeness1/5

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

For a simple tool with one parameter and no output schema, the description should at least clarify what happens when invoked. It omits key context such as response handling, required app, and typical use case, making it incomplete.

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 100% and the parameter 'prompt' has a description ('Send to ChatGPT'). The tool description adds no extra semantics beyond the schema, so baseline 3 is appropriate.

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

Purpose2/5

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

The description 'An AI agent that utilizes the ChatGPT app for macOS' is vague; it fails to specify the action (e.g., sending a prompt) or the result (e.g., returning a response). It reads like a label rather than a clear purpose statement.

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?

No guidance is provided on when to use this tool or when to avoid it. There are no sibling tools or alternatives mentioned, leaving the agent without context for appropriate invocation.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.5/5.0
Disambiguation5/5

With only one tool, there is no risk of confusion. The tool's purpose is clearly defined and distinct from any other possible tools.

Naming Consistency5/5

Since there is only one tool, naming consistency is not applicable; a single tool cannot have inconsistencies. The name 'ask_via_shortcuts_cli' is descriptive and follows a reasonable pattern.

Tool Count3/5

A single tool is at the lower end of what is reasonable. For a server targeting ChatGPT Mac app interaction, one tool feels thin but may be justified if the intended use case is very narrow.

Completeness2/5

The tool set lacks many expected operations for interacting with an AI assistant, such as handling conversations, retrieving responses in different formats, or managing configurations. The surface is significantly incomplete for its domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

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/yimajo/mcp-server-chatgpt-mac-app'

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