NanoGPT MCP Server
The NanoGPT MCP Server allows you to integrate NanoGPT’s powerful AI capabilities directly into your favorite AI tools and editors that support the Model Context Protocol (MCP). With this server, you can give your AI agents access to web search, image generation, URL scraping, and NanoGPT’s full library of LLMs.Installation
You can run the NanoGPT MCP server directly usingnpx. No manual installation is required if you have Node.js installed.
Claude Code
To add NanoGPT MCP to Claude Code via the CLI:YOUR_API_KEY with your actual NanoGPT API key.
IDE Integration
To use NanoGPT MCP with tools like Claude Desktop, Cline, or Cursor, add the following to your configuration file:Configuration
The server is configured via environment variables.| Variable | Description | Default |
|---|---|---|
NANOGPT_API_KEY | Required. Your NanoGPT API key. | - |
NANOGPT_BASE_URL | The base URL for the NanoGPT API. | https://nano-gpt.com |
NANOGPT_AUTH_MODE | Authentication mode (bearer, x-api-key, or both). | bearer |
NANOGPT_LOG_LEVEL | Logging verbosity (debug, info, warn, error). | info |
NANOGPT_TIMEOUT_MS | Request timeout in milliseconds. | 120000 |
NANOGPT_MAX_RETRIES | Number of times to retry failed requests. | 0 |
NANOGPT_DEFAULT_MODEL | Default model to use for chat tools. | - |
Available Tools
The MCP server exposes several tools that your AI agent can use:chat: Send messages to any model supported by NanoGPT.image-generation: Generate images using models like Flux, DALL-E 3, etc.web-search: Search the web and get back clean, LLM-friendly results.scrape-urls: Extract content from one or more websites.youtube-transcribe: Get transcripts from YouTube videos.balance: Check your current NanoGPT account balance.list-models: List available text, image, audio, or video models.vision: Analyze images using vision-capable models.
Tool Parameters
chat
messages(required): Array of message objects (role+content)model(optional): Model ID to use for the requesttemperature(optional): Sampling temperaturemax_tokens(optional): Maximum tokens in the response
image-generation
prompt(required): Text description of the image to generatemodel(optional): Image model IDn(optional): Number of images to generate (1–10)size(optional): Dimensions (e.g.,1024x1024)quality(optional): Quality setting (model-dependent)
web-search
query(required): Search query stringdepth(optional):standardordeepfromDate/toDate(optional): Date range filter (YYYY-MM-DD)
youtube-transcribe
urls(required): Array of YouTube URLs (up to 10 per request)
Resources
Resources allow agents to “read” data stored by the server. NanoGPT MCP provides:nanogpt://raw/{id}: Access the raw JSON response from a previous API call.nanogpt://image/{id}: Access an image generated during the session.
Cost & Billing
- Paid tools deduct from your NanoGPT account balance.
- Model listing operations are complimentary.
- Failed requests (timeouts, errors) are not charged.
Troubleshooting
API key validation
- Ensure
NANOGPT_API_KEYis set in your MCP client configuration. - Verify the key in your NanoGPT API dashboard and remove any extra spaces.
Timeouts for long operations
Increase the timeout for web search or large jobs withNANOGPT_TIMEOUT_MS:
Node.js version compatibility
The MCP server requires Node.js 22+:MCP client connection checks
- Re-add the server configuration if your client can’t connect.
- Review your MCP client logs for connection errors.
Getting Started
- Get your API key from the NanoGPT API dashboard.
- Configure your MCP client (like Claude Desktop) with the server settings.
- Start chatting with your agent and ask it to “Search the web for…” or “Generate an image of…”.