Metadata-Version: 2.4
Name: gandr-mcp
Version: 0.2.0
Summary: The official Gandr MCP server: setup help from the live docs, and text to speech inside any MCP-compatible agent
Author-email: Gandr <team@gandr.ai>
License: MIT
Project-URL: Homepage, https://gandr.ai
Project-URL: Repository, https://github.com/Gandr-AI/gandr-mcp
Keywords: mcp,tts,text-to-speech,voice-ai,agents
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mcp<2,>=1.9
Dynamic: license-file

# gandr-mcp

The official **Gandr MCP server**. It does two jobs inside any MCP-compatible agent (Claude Code, Claude Desktop, Cursor and others):

1. **Sets Gandr up for you.** Ask your agent to add Gandr text to speech to your project. It reads the live Gandr developer docs through this server and writes the integration for your stack. These tools need no API key.
2. **Speaks.** Render text to speech from the agent with your Gandr key.

## Tools

| Tool | What it does |
|---|---|
| `get_setup_guide` | Step-by-step setup and working code for your stack: python, node, livekit, pipecat, vapi, langchain, crewai, haystack, ai-sdk, n8n, dify, openai, rest, mcp. |
| `list_integrations` | Every stack with a setup guide. |
| `search_docs` | Search the Gandr developer docs: endpoints, request fields, voices, errors, limits, pricing. |
| `read_docs` | Read one docs section in full, or list the sections. |
| `synthesize` | Render text to speech (WAV, base64). Voice, language, sample rate 8000-48000, pitch and pacing dials. |
| `list_voices` | The six available voices. |
| `list_languages` | The 23 supported languages and their codes. |
| `get_usage` | Tokens used by the configured key. One token is one character. |

The docs tools read [gandr.ai/llms.txt](https://gandr.ai/llms.txt) live and fall back to a copy shipped in the package.

## Install

```bash
pip install gandr-mcp
```

Claude Code:

```bash
claude mcp add gandr -e GANDR_API_KEY=gnd_... -- gandr-mcp
```

Claude Desktop (add to `claude_desktop_config.json`), Cursor (`.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "gandr": {
      "command": "gandr-mcp",
      "env": {
        "GANDR_API_KEY": "gnd_..."
      }
    }
  }
}
```

Then ask: "Add Gandr text to speech to this project."

Get a free key with 50,000 tokens at [gandr.ai/join](https://gandr.ai/join). Docs: [gandr.ai/docs](https://gandr.ai/docs).

---

mcp-name: io.github.Gandr-AI/gandr-mcp
