# DynaRoute MCP Server
A Model Context Protocol (MCP) server that provides intelligent chat completions with automatic model routing and cost optimization through DynaRoute.
## Features
- 🧠 **Intelligent Model Routing**: Automatically routes queries to the most cost-effective model while maintaining quality
- 💰 **Cost Optimization**: Save up to 70% compared to premium models like GPT-4o
- 📊 **Detailed Analytics**: Get comprehensive metrics including token usage, costs, and performance data
- 🔍 **Routing Intelligence**: See exactly which model was selected and why
- ⚡ **Easy Integration**: Works seamlessly with Claude Desktop, Cursor, and other MCP-compatible clients
## Installation
Install via pip:
```bash
pip install dynaroute-mcp-server
```
## Quick Start
1. **Get your DynaRoute API key** from [DynaRoute](https://dynaroute.vizuara.com/)
2. **Configure Claude Desktop** by adding this to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"dynaroute": {
"command": "uv",
"args": ["tool", "run", "dynaroute-mcp-server"],
"env": {
"DYNAROUTE_API_KEY": "YOUR_API_KEY"
}
}
}
}
```
3. **Restart Claude Desktop** and start using DynaRoute!
## Usage
Once configured, you can use DynaRoute in Claude Desktop by:
- **Asking for AI responses**: "Use DynaRoute to explain quantum computing"
- **Requesting cost analysis**: "Get a cost-optimized response about machine learning"
- **Explicit tool usage**: "Use the DynaRoute tool to answer this question"
## Example Output
When you use the DynaRoute tool, you'll get:
```
🤖 DynaRoute Response:
[Your AI response content here]
📊 PERFORMANCE METRICS:
• Model Used: gcp-gemini-2.0-flash-thinking
• Response Time: 2.5 seconds
• Request ID: chatcmpl-xyz123
🔢 TOKEN USAGE:
• Input Tokens: 25
• Output Tokens: 150
• Total Tokens: 175
💰 COST BREAKDOWN:
• Input Cost: $0.000012
• Output Cost: $0.000045
• Total Cost: $0.000057
📈 COST SAVINGS vs GPT-4o:
• GPT-4o Equivalent Cost: $0.000175
• Your Actual Cost: $0.000057
• Money Saved: $0.000118
• Savings Percentage: 67.4%
✅ EFFICIENCY SUMMARY: DynaRoute saved you 67.4% compared to GPT-4o while maintaining quality!
```
## Configuration
### Environment Variables
- `DYNAROUTE_API_KEY`: Your DynaRoute API key (required)
### Tool Parameters
The `dynaroute_chat` tool accepts:
- `messages`: Array of conversation messages (required)
- `level_override`: Override complexity level 1-5 (optional)
## Claude Desktop Configuration
Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):
```json
{
"mcpServers": {
"dynaroute": {
"command": "uv",
"args": ["tool", "run", "dynaroute-mcp-server"],
"env": {
"DYNAROUTE_API_KEY": "YOUR_API_KEY"
}
}
}
}
```
## Other MCP Clients
### Cursor IDE
Add to your Cursor settings:
```json
{
"mcp": {
"servers": {
"dynaroute": {
"command": "uv",
"args": ["tool", "run", "dynaroute-mcp-server"],
"env": {
"DYNAROUTE_API_KEY": "YOUR_API_KEY"
}
}
}
}
}
```
### Custom Usage
You can also import and use the server programmatically:
```python
import asyncio
from dynaroute_mcp import DynaRouteMCPServer
async def main():
server = DynaRouteMCPServer(api_key="your_api_key")
await server.run()
asyncio.run(main())
```
## Requirements
- Python 3.8+
- DynaRoute API key
- MCP-compatible client (Claude Desktop, Cursor, etc.)
## Dependencies
- `mcp`: Model Context Protocol implementation
- `dynaroute-client`: Official DynaRoute Python client
## License
MIT License
## Support
- 📧 Email: abraar237@gmail.com
- 🐛 Issues: [GitHub Issues](https://github.com/abraar237/dynaroute-mcp-server/issues)
- 📖 Documentation: [GitHub README](https://github.com/abraar237/dynaroute-mcp-server)
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## Changelog
### 1.0.0
- Initial release
- DynaRoute integration with MCP
- Cost optimization and analytics
- Claude Desktop support
Raw data
{
"_id": null,
"home_page": null,
"name": "dynaroute-mcp-server",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "mcp, dynaroute, ai, llm, cost-optimization, model-routing",
"author": null,
"author_email": "Mohammed Abraar <abraar237@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/a6/56/a9d949e88a6b81b25b47d07dde137ba7b2d25b897625c3543e74fe920f87/dynaroute_mcp_server-1.0.2.tar.gz",
"platform": null,
"description": "# DynaRoute MCP Server\n\nA Model Context Protocol (MCP) server that provides intelligent chat completions with automatic model routing and cost optimization through DynaRoute.\n\n## Features\n\n- \ud83e\udde0 **Intelligent Model Routing**: Automatically routes queries to the most cost-effective model while maintaining quality\n- \ud83d\udcb0 **Cost Optimization**: Save up to 70% compared to premium models like GPT-4o\n- \ud83d\udcca **Detailed Analytics**: Get comprehensive metrics including token usage, costs, and performance data\n- \ud83d\udd0d **Routing Intelligence**: See exactly which model was selected and why\n- \u26a1 **Easy Integration**: Works seamlessly with Claude Desktop, Cursor, and other MCP-compatible clients\n\n## Installation\n\nInstall via pip:\n\n```bash\npip install dynaroute-mcp-server\n```\n\n## Quick Start\n\n1. **Get your DynaRoute API key** from [DynaRoute](https://dynaroute.vizuara.com/)\n\n2. **Configure Claude Desktop** by adding this to your `claude_desktop_config.json`:\n ```json\n {\n \"mcpServers\": {\n \"dynaroute\": {\n \"command\": \"uv\",\n \"args\": [\"tool\", \"run\", \"dynaroute-mcp-server\"],\n \"env\": {\n \"DYNAROUTE_API_KEY\": \"YOUR_API_KEY\"\n }\n }\n }\n }\n ```\n\n3. **Restart Claude Desktop** and start using DynaRoute!\n\n## Usage\n\nOnce configured, you can use DynaRoute in Claude Desktop by:\n\n- **Asking for AI responses**: \"Use DynaRoute to explain quantum computing\"\n- **Requesting cost analysis**: \"Get a cost-optimized response about machine learning\"\n- **Explicit tool usage**: \"Use the DynaRoute tool to answer this question\"\n\n## Example Output\n\nWhen you use the DynaRoute tool, you'll get:\n\n```\n\ud83e\udd16 DynaRoute Response:\n[Your AI response content here]\n\n\ud83d\udcca PERFORMANCE METRICS:\n\u2022 Model Used: gcp-gemini-2.0-flash-thinking\n\u2022 Response Time: 2.5 seconds\n\u2022 Request ID: chatcmpl-xyz123\n\n\ud83d\udd22 TOKEN USAGE:\n\u2022 Input Tokens: 25\n\u2022 Output Tokens: 150\n\u2022 Total Tokens: 175\n\n\ud83d\udcb0 COST BREAKDOWN:\n\u2022 Input Cost: $0.000012\n\u2022 Output Cost: $0.000045\n\u2022 Total Cost: $0.000057\n\n\ud83d\udcc8 COST SAVINGS vs GPT-4o:\n\u2022 GPT-4o Equivalent Cost: $0.000175\n\u2022 Your Actual Cost: $0.000057\n\u2022 Money Saved: $0.000118\n\u2022 Savings Percentage: 67.4%\n\n\u2705 EFFICIENCY SUMMARY: DynaRoute saved you 67.4% compared to GPT-4o while maintaining quality!\n```\n\n## Configuration\n\n### Environment Variables\n\n- `DYNAROUTE_API_KEY`: Your DynaRoute API key (required)\n\n### Tool Parameters\n\nThe `dynaroute_chat` tool accepts:\n\n- `messages`: Array of conversation messages (required)\n- `level_override`: Override complexity level 1-5 (optional)\n\n## Claude Desktop Configuration\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS):\n\n```json\n{\n \"mcpServers\": {\n \"dynaroute\": {\n \"command\": \"uv\",\n \"args\": [\"tool\", \"run\", \"dynaroute-mcp-server\"],\n \"env\": {\n \"DYNAROUTE_API_KEY\": \"YOUR_API_KEY\"\n }\n }\n }\n}\n```\n\n## Other MCP Clients\n\n### Cursor IDE\nAdd to your Cursor settings:\n```json\n{\n \"mcp\": {\n \"servers\": {\n \"dynaroute\": {\n \"command\": \"uv\",\n \"args\": [\"tool\", \"run\", \"dynaroute-mcp-server\"],\n \"env\": {\n \"DYNAROUTE_API_KEY\": \"YOUR_API_KEY\"\n }\n }\n }\n }\n}\n```\n\n### Custom Usage\nYou can also import and use the server programmatically:\n\n```python\nimport asyncio\nfrom dynaroute_mcp import DynaRouteMCPServer\n\nasync def main():\n server = DynaRouteMCPServer(api_key=\"your_api_key\")\n await server.run()\n\nasyncio.run(main())\n```\n\n## Requirements\n\n- Python 3.8+\n- DynaRoute API key\n- MCP-compatible client (Claude Desktop, Cursor, etc.)\n\n## Dependencies\n\n- `mcp`: Model Context Protocol implementation\n- `dynaroute-client`: Official DynaRoute Python client\n\n## License\n\nMIT License\n\n## Support\n\n- \ud83d\udce7 Email: abraar237@gmail.com\n- \ud83d\udc1b Issues: [GitHub Issues](https://github.com/abraar237/dynaroute-mcp-server/issues)\n- \ud83d\udcd6 Documentation: [GitHub README](https://github.com/abraar237/dynaroute-mcp-server)\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## Changelog\n\n### 1.0.0\n- Initial release\n- DynaRoute integration with MCP\n- Cost optimization and analytics\n- Claude Desktop support\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "MCP server for DynaRoute - intelligent chat completions with automatic model routing and cost optimization",
"version": "1.0.2",
"project_urls": {
"Documentation": "https://github.com/abraar237/dynaroute-mcp-server#readme",
"Homepage": "https://github.com/abraar237/dynaroute-mcp-server",
"Issues": "https://github.com/abraar237/dynaroute-mcp-server/issues",
"Repository": "https://github.com/abraar237/dynaroute-mcp-server"
},
"split_keywords": [
"mcp",
" dynaroute",
" ai",
" llm",
" cost-optimization",
" model-routing"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ee364b3186374a21fba35f7abcfa2182ab51a6bac87aa881e3d53b96abd406ef",
"md5": "635ca00a88ea7974d380d76f6a994cd4",
"sha256": "bfb9783e89d3aef913ad06fb3a04c657fb8cccd00ed87fdf91b50f193ff2d279"
},
"downloads": -1,
"filename": "dynaroute_mcp_server-1.0.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "635ca00a88ea7974d380d76f6a994cd4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 8325,
"upload_time": "2025-07-08T11:34:43",
"upload_time_iso_8601": "2025-07-08T11:34:43.458731Z",
"url": "https://files.pythonhosted.org/packages/ee/36/4b3186374a21fba35f7abcfa2182ab51a6bac87aa881e3d53b96abd406ef/dynaroute_mcp_server-1.0.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "a656a9d949e88a6b81b25b47d07dde137ba7b2d25b897625c3543e74fe920f87",
"md5": "26f5a65009fc2a91428097633b8e0ee0",
"sha256": "73a328917470f6edab05f9371f016d174523ea1b887ba189f2b07144204da678"
},
"downloads": -1,
"filename": "dynaroute_mcp_server-1.0.2.tar.gz",
"has_sig": false,
"md5_digest": "26f5a65009fc2a91428097633b8e0ee0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 7369,
"upload_time": "2025-07-08T11:34:44",
"upload_time_iso_8601": "2025-07-08T11:34:44.905500Z",
"url": "https://files.pythonhosted.org/packages/a6/56/a9d949e88a6b81b25b47d07dde137ba7b2d25b897625c3543e74fe920f87/dynaroute_mcp_server-1.0.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-08 11:34:44",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "abraar237",
"github_project": "dynaroute-mcp-server#readme",
"github_not_found": true,
"lcname": "dynaroute-mcp-server"
}
JSON
