Skip to main content

NanoGPT MCP Integration

The NanoGPT MCP (Model Context Protocol) server allows you to use NanoGPT’s AI capabilities directly from MCP-compatible clients like Claude Code, Cursor, and other AI coding assistants.

Features

The NanoGPT MCP server provides the following tools:
ToolDescription
nanogpt_chatSend chat messages to any AI model available on NanoGPT
nanogpt_get_balanceCheck your account balance (USD and Nano)
nanogpt_image_generateGenerate images using DALL-E, Flux, Midjourney, and more
nanogpt_web_searchSearch the web for current information
nanogpt_scrape_urlsExtract content from web pages
nanogpt_youtube_transcribeGet transcripts from YouTube videos
nanogpt_list_text_modelsList available text/chat models
nanogpt_list_image_modelsList available image generation models
nanogpt_list_audio_modelsList available audio models (TTS/STT)
nanogpt_list_video_modelsList available video generation models
nanogpt_visionAnalyze images with vision-capable models

Prerequisites

  • A NanoGPT account with an API key (get one here)
  • Node.js 22.x or later
  • An MCP-compatible client (Claude Code, Cursor, etc.)

Installation

The easiest way to use the NanoGPT MCP server is via npx.

Claude Code

macOS / Linux
claude mcp add nanogpt --scope user \
  --env NANOGPT_API_KEY=YOUR_API_KEY \
  -- npx -y @nanogpt/mcp
Windows
claude mcp add nanogpt --scope user --env NANOGPT_API_KEY=YOUR_API_KEY -- cmd /c "C:\Program Files\nodejs\npx.cmd" -y @nanogpt/mcp
On native Windows, npx is usually a .cmd shim, so it should be launched through cmd /c. If you use WSL, run the macOS/Linux command inside WSL instead of the native Windows one. Claude Code’s MCP CLI syntax has changed over time. If you copied an older NanoGPT command, remove the existing nanogpt MCP entry and add it again using the commands on this page. An immediate Invalid API key error can be caused by a broken MCP launcher command, not just a bad key value.
Replace YOUR_API_KEY with your actual NanoGPT API key.

Option 2: Global Installation

npm install -g @nanogpt/mcp
Then add to your MCP client:
claude mcp add nanogpt --scope user \
  --env NANOGPT_API_KEY=YOUR_API_KEY \
  -- nanogpt-mcp

Configuration

Required Environment Variables

VariableDescription
NANOGPT_API_KEYYour NanoGPT API key (required)

Optional Environment Variables

VariableDefaultDescription
NANOGPT_TIMEOUT_MS600000 (10 min)Request timeout in milliseconds
NANOGPT_DEFAULT_MODELclaude-sonnet-4-5-20250929Default model for chat requests
NANOGPT_LOG_LEVELinfoLog level: debug, info, warn, error
NANOGPT_BASE_URLhttps://nano-gpt.comBase URL for the NanoGPT API
NANOGPT_AUTH_MODEbearerAuth mode: bearer, x-api-key, or both
NANOGPT_MAX_RETRIES0Number of retry attempts

Usage Examples

Once configured, you can use NanoGPT tools directly from your MCP client. Here are some examples:

Check Your Balance

Ask your AI assistant:
“Check my NanoGPT balance”
The assistant will call nanogpt_get_balance and show your USD and Nano balances.

Chat with AI Models

“Use NanoGPT to ask Claude Sonnet about the best practices for REST API design”

Generate Images

“Use NanoGPT to generate an image of a futuristic city at sunset”

Analyze Images

“Use NanoGPT vision to analyze this product photo”

Search the Web

“Use NanoGPT web search to find the latest news about AI”

Get YouTube Transcripts

“Use NanoGPT to get the transcript of this YouTube video: https://www.youtube.com/watch?v=…”

Scrape Web Pages

“Use NanoGPT to scrape the content from https://example.com

Tool Reference

nanogpt_chat

Send a chat completion request to an AI model. Parameters:
  • messages (required): Array of message objects with role (“system”, “user”, “assistant”) and content
  • model (optional): Model ID (defaults to Claude Sonnet 4.5)
  • temperature (optional): Sampling temperature (0-2)
  • max_tokens (optional): Maximum tokens in response
Example:
{
  "messages": [
    {"role": "user", "content": "Explain quantum computing in simple terms"}
  ],
  "model": "openai/gpt-5.2"
}

nanogpt_get_balance

Check your current account balance. Parameters: None Returns:
  • usd_balance: Balance in USD
  • nano_balance: Balance in Nano (XNO)
  • nanoDepositAddress: Your Nano deposit address

nanogpt_image_generate

Generate images from text prompts. Parameters:
  • prompt (required): Text description of the image to generate
  • model (optional): Image model to use (e.g., “dall-e-3”, “flux-pro”)
  • n (optional): Number of images to generate (1-10)
  • size (optional): Image size (e.g., “1024x1024”)
  • quality (optional): Image quality setting
Example:
{
  "prompt": "A serene mountain landscape at dawn",
  "model": "flux-pro",
  "size": "1024x1024"
}
Search the web for current information. Parameters:
  • query (required): Search query
  • depth (optional): “standard” or “deep”
  • outputType (optional): “searchResults”, “sourcedAnswer”, or “structured”
  • includeImages (optional): Include image results
  • fromDate / toDate (optional): Date range filter (YYYY-MM-DD)
Example:
{
  "query": "latest developments in fusion energy",
  "depth": "deep",
  "outputType": "sourcedAnswer"
}

nanogpt_vision

Analyze images using vision-capable models. Parameters:
  • messages (required): Array of message objects with text and image content blocks
  • model (optional): Vision-capable model ID
  • temperature (optional): Sampling temperature (0-2)
  • max_tokens (optional): Maximum tokens in response
Example:
{
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "What issues do you see in this image?" },
        {
          "type": "image",
          "source": {
            "type": "url",
            "url": "https://example.com/photo.jpg"
          }
        }
      ]
    }
  ],
  "model": "openai/gpt-5.2"
}

nanogpt_scrape_urls

Scrape content from web pages. Parameters:
  • urls (required): Array of URLs to scrape (max 5 per request)
  • mode (optional): “scrape-page” or “conversation”
  • stealthMode (optional): Use stealth mode for scraping
Example:
{
  "urls": ["https://example.com/article1", "https://example.com/article2"]
}

nanogpt_youtube_transcribe

Get transcripts from YouTube videos. Parameters:
  • urls (required): Array of YouTube URLs (max 10 per request)
Example:
{
  "urls": ["https://www.youtube.com/watch?v=dQw4w9WgXcQ"]
}

nanogpt_list_text_models

List available text/chat models. Parameters:
  • detailed (optional): Include pricing information (default: false)

nanogpt_list_image_models

List available image generation models. Parameters:
  • detailed (optional): Include pricing information (default: true)

nanogpt_list_audio_models

List available audio models. Parameters:
  • detailed (optional): Include pricing information (default: true)
  • type (optional): Filter by type: “tts”, “stt”, or “all”

nanogpt_list_video_models

List available video generation models. Parameters:
  • detailed (optional): Include pricing information (default: true)

Resources

Resources allow agents to access data saved during a session:
  • nanogpt://raw/{id}: Raw JSON response from a previous API call
  • nanogpt://image/{id}: Generated images stored during the session

Error Handling

The MCP server provides clear error messages for common issues:
ErrorMeaningSolution
Invalid API keyAuthentication failedCheck your NANOGPT_API_KEY and MCP launch command
Insufficient balanceAccount balance too lowTop up your account at nano-gpt.com
Rate limitedToo many requestsWait and try again
TimeoutRequest took too longTry a simpler request or increase NANOGPT_TIMEOUT_MS

Billing

  • All paid tools deduct from your NanoGPT balance
  • Use nanogpt_get_balance to check your balance before expensive operations
  • Model listing tools are free to use
  • Failed requests (timeouts, errors) are not charged

Troubleshooting

”Missing required env var: NANOGPT_API_KEY”

macOS / Linux
claude mcp add nanogpt --scope user \
  --env NANOGPT_API_KEY=your_actual_key_here \
  -- npx -y @nanogpt/mcp
Windows
claude mcp add nanogpt --scope user --env NANOGPT_API_KEY=your_actual_key_here -- cmd /c "C:\Program Files\nodejs\npx.cmd" -y @nanogpt/mcp
Make sure you set your API key when adding the MCP server. If you re-add the server later, include --env NANOGPT_API_KEY=... again.

”Invalid API key” errors

An immediate Invalid API key error can be caused by a broken MCP launcher command, not just a bad key value.
  1. Verify your API key at nano-gpt.com/api
  2. Make sure you’re using the full API key value
  3. Check for extra spaces or newlines in the key
  4. Verify that your Claude Code MCP launch command is correct, especially on Windows where npx should be run via cmd /c "C:\Program Files\nodejs\npx.cmd".

Requests timing out

For long-running operations like web search, you can increase the timeout: macOS / Linux
claude mcp add nanogpt --scope user \
  --env NANOGPT_API_KEY=your_key \
  --env NANOGPT_TIMEOUT_MS=900000 \
  -- npx -y @nanogpt/mcp
Windows
claude mcp add nanogpt --scope user --env NANOGPT_API_KEY=your_key --env NANOGPT_TIMEOUT_MS=900000 -- cmd /c "C:\Program Files\nodejs\npx.cmd" -y @nanogpt/mcp

MCP server not connecting

  1. Ensure Node.js 22+ is installed: node --version
  2. Try removing and re-adding the MCP server
  3. Check your MCP client’s logs for detailed error messages
  4. If you already added NanoGPT using an older command, remove the existing nanogpt MCP entry and add it again with the updated command

Support

Privacy & Security

  • Your API key is stored locally and only sent to NanoGPT servers
  • The MCP server runs locally on your machine
  • No data is logged or stored by the MCP server
  • Chat messages and other content are processed according to NanoGPT’s privacy policy