chatgpt-cli
ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports OpenAI, Azure, Perplexity, LLaMA, and more, with features like streaming, interactive chat, prompt files, image/audio I/O, MCP tool calls, and an experimental agent mode for safe, multi-step au
ChatGPT CLI is a multi-provider command-line interface that functions as an MCP server, enabling AI agents to integrate external tools and services through the Model Context Protocol. It supports both HTTP and STDIO MCP connections, allowing clients to call tools, manage sessions automatically, and inject results back into conversation context. The server works with OpenAI, Azure, Perplexity, LLaMA, and other providers, featuring streaming responses, interactive chat, image/audio processing, and an experimental agent mode with ReAct and Plan/Execute workflows. Developers can use it to extend AI assistants with custom tool integrations while maintaining safety through budget limits and policy enforcement.
Key Features
Use Cases
- 01Integrating external MCP tools like weather APIs or web scrapers into AI workflows
- 02Building multi-step autonomous agents that can execute shell commands and file operations
- 03Creating conversational interfaces that maintain context across multiple CLI sessions
- 04Processing audio transcriptions and generating speech from text responses
- 05Generating and editing images using GPT-powered models with prompt engineering
- 06Connecting AI assistants to enterprise services via Azure or custom API gateways
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
chatgpt-cli — FAQ
What is chatgpt-cli MCP server?+
It's a command-line MCP server that implements the Model Context Protocol, allowing AI clients to call external tools via HTTP or STDIO, with automatic session management and context injection. It supports multiple LLM providers and includes agent capabilities with safety controls.
How do I install chatgpt-cli?+
Install via Homebrew with 'brew tap kardolus/chatgpt-cli && brew install chatgpt-cli', or download the pre-built binary for your platform from the GitHub releases page. Set your OPENAI_API_KEY environment variable to get started.
Which AI clients work with this MCP server?+
Any client that supports the Model Context Protocol over HTTP or STDIO can connect. The server can also function as a standalone CLI tool for direct interaction with LLMs.
Do I need an API key?+
Yes, you need an API key from your chosen provider (OpenAI, Azure, Perplexity, etc.). Set it via the OPENAI_API_KEY environment variable or configure it in the config.yaml file.
Is chatgpt-cli free to use?+
The CLI tool itself is open-source and free. However, you'll incur costs from your LLM provider based on token usage and API calls.
How do I call MCP tools with chatgpt-cli?+
Use the --mcp flag with your endpoint URL, --mcp-tool for the tool name, and --mcp-param for arguments. The CLI handles session initialization automatically and injects results into the conversation context.
How do I install chatgpt-cli?+
Open the source repository on GitHub and follow its README. chatgpt-cli is a mcp server — MCP Agents Market links you directly to the official repo.
Is chatgpt-cli free?+
chatgpt-cli is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.