GPT2099 Nu
a Nushell cross.stream extension to interact with LLMs and MCP servers
What is GPT2099 Nu?
GPT2099 Nu is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to nushell cross.stream extension to interact with llms and mcp servers
a Nushell cross.stream extension to interact with LLMs and MCP servers
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- a Nushell cross.stream extension to interact with LLMs and M
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gpt2099-nuConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use GPT2099 Nu
gpt2099.nu is a Nushell extension built on the cross.stream framework that brings LLM interaction and MCP server connectivity natively into the Nushell shell environment, supporting Anthropic, Cerebras, Cohere, Gemini, and OpenAI providers through a unified command interface. It allows Nushell users to pipe shell data directly into LLM prompts, chat with configurable model aliases, connect to external MCP servers to extend tool capabilities, and process documents including PDFs, images, and text files — all within the structured data model Nushell is known for. Developers and power users who live in the terminal and want to integrate AI into shell pipelines without switching to a chat UI use it to compose LLM calls with Nushell's native stream and filter primitives.
Prerequisites
- Nushell installed (nu shell, https://www.nushell.sh)
- cross.stream installed (https://cablehead.github.io/xs/getting-started/installation/)
- API keys for at least one supported provider: Anthropic, OpenAI, Gemini, Cohere, or Cerebras
- The gpt2099.nu repository cloned locally
Install cross.stream
gpt2099.nu requires cross.stream as its runtime dependency. Follow the installation guide at https://cablehead.github.io/xs/getting-started/installation/ for your platform.
Clone the gpt2099.nu repository
Clone the repository so you have the gpt overlay files available to load in Nushell.
git clone https://github.com/cablehead/gpt2099.nu.git
cd gpt2099.nuLoad the gpt overlay in Nushell
Use the overlay use command to load the gpt2099 commands into your Nushell session. The -pr flags make it persistent and record the source path.
overlay use -pr ./gptInitialize and enable a provider
Run gpt init to set up the configuration store, then enable your preferred LLM provider. You will be prompted to enter your API key.
gpt init
gpt provider enableSet a model alias and test
Create a short alias for your preferred model, then pipe a string into gpt to confirm everything is working.
# Set an alias called 'milli' for a fast model
gpt provider ptr milli --set
# Test it
"hola" | gpt -p milliConnect to an MCP server (optional)
Use gpt's MCP integration to connect to external MCP servers and extend the available tools within your Nushell LLM sessions.
GPT2099 Nu Examples
Client configuration
gpt2099.nu is a Nushell-native tool, not a traditional MCP server with a JSON config. The equivalent setup is loading the overlay and setting a provider in Nushell. For connecting gpt2099.nu as an MCP server to another client, use the stdio transport.
{
"mcpServers": {
"gpt2099-nu": {
"command": "nu",
"args": ["-c", "overlay use -pr /path/to/gpt2099.nu/gpt; gpt serve"]
}
}
}Prompts to try
Example Nushell commands that leverage gpt2099.nu for LLM interaction and pipeline integration.
- Pipe shell output into an LLM: "ls | to json | gpt -p milli 'which file is largest and why might that be a concern?'"
- Summarize a log file: "open server.log | gpt -p milli 'summarize the errors from the last hour'"
- Process a PDF document: "gpt file ~/report.pdf | gpt -p milli 'extract the executive summary'"
- Switch providers mid-session: "gpt provider ptr fast --set" then "'explain closures in Rust' | gpt -p fast"Troubleshooting GPT2099 Nu
overlay use fails with 'module not found' error
Ensure you are running the overlay use command from within the cloned gpt2099.nu directory, or provide the full absolute path to the gpt overlay file. The path must point to the gpt file/directory inside the repo.
gpt provider enable does not prompt for an API key
Run 'gpt init' first to initialize the configuration store before enabling a provider. If the store already exists and is corrupted, check the cross.stream data directory and clear stale state.
API authentication errors when calling gpt
API keys are stored per-provider during the 'gpt provider enable' step. Re-run 'gpt provider enable' for the affected provider and re-enter the correct API key. Confirm the key is valid by testing it directly against the provider's API.
Frequently Asked Questions about GPT2099 Nu
What is GPT2099 Nu?
GPT2099 Nu is a Model Context Protocol (MCP) server that nushell cross.stream extension to interact with llms and mcp servers It connects AI assistants to external tools and data sources through a standardized interface.
How do I install GPT2099 Nu?
Follow the installation instructions on the GPT2099 Nu GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with GPT2099 Nu?
GPT2099 Nu works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is GPT2099 Nu free to use?
Yes, GPT2099 Nu is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
GPT2099 Nu Alternatives — Similar Coding Agents Servers
Looking for alternatives to GPT2099 Nu? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up GPT2099 Nu in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use GPT2099 Nu?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.