# trackio-mcp
[](https://badge.fury.io/py/trackio-mcp)
[](https://opensource.org/licenses/MIT)
[](https://github.com/fcakyon/trackio-mcp/actions)
**MCP (Model Context Protocol) server support for trackio experiment tracking**
This package enables AI agents to observe and interact with [trackio](https://github.com/gradio-app/trackio) experiments through the Model Context Protocol (MCP). Simply import `trackio_mcp` before `trackio` to automatically enable MCP server functionality.
## Features
- **Zero-code integration**: Just import `trackio_mcp` before `trackio`
- **Automatic MCP server**: Enables MCP server on all trackio deployments (local & Spaces)
- **Rich tool set**: Exposes trackio functionality as MCP tools for AI agents
- **Spaces compatible**: Works seamlessly with Hugging Face Spaces deployments
- **Drop-in replacement**: No changes needed to existing trackio code
## Installation
```bash
pip install trackio-mcp
```
Or with development dependencies:
```bash
pip install trackio-mcp[dev]
```
## Quick Start
### Basic Usage
Simply import `trackio_mcp` before importing `trackio`:
```python
import trackio_mcp # This enables MCP server functionality
import trackio as wandb
# Your existing trackio code works unchanged
wandb.init(project="my-experiment")
wandb.log({"loss": 0.1, "accuracy": 0.95})
wandb.finish()
```
The MCP server will be automatically available at:
- **Local**: `http://localhost:7860/gradio_api/mcp/sse`
- **Spaces**: `https://your-space.hf.space/gradio_api/mcp/sse`
### Deploy to Hugging Face Spaces with MCP
```python
import trackio_mcp
import trackio as wandb
# Deploy to Spaces with MCP enabled automatically
wandb.init(
project="my-experiment",
space_id="username/my-trackio-space"
)
wandb.log({"loss": 0.1})
wandb.finish()
```
### Standalone MCP Server
Launch a dedicated MCP server for trackio tools:
```python
from trackio_mcp.tools import launch_trackio_mcp_server
# Launch standalone MCP server on port 7861
launch_trackio_mcp_server(port=7861, share=False)
```
## Available MCP Tools
Once connected, AI agents can use these trackio tools:
### Core Tools (via Gradio API)
- **log**: Log metrics to a trackio run
- **upload_db_to_space**: Upload local database to a Space
### Extended Tools (via trackio-mcp)
- **get_projects**: List all trackio projects
- **get_runs**: Get runs for a specific project
- **filter_runs**: Filter runs by name pattern
- **get_run_metrics**: Get metrics data for a specific run
- **get_available_metrics**: Get all available metric names for a project
- **load_run_data**: Load and process run data with optional smoothing
- **get_project_summary**: Get comprehensive project statistics
### Example Agent Interaction
```
Human: "Show me the latest results from my 'image-classification' project"
Agent: I'll check your trackio projects and get the latest results.
[Tool: get_projects] → finds "image-classification" project
[Tool: get_runs] → gets runs for "image-classification"
[Tool: get_run_metrics] → gets metrics for latest run
[Tool: get_available_metrics] → gets metric names
Agent: Your latest image-classification run achieved 94.2% accuracy with a final loss of 0.18. The model trained for 50 epochs with best validation accuracy of 94.7% at epoch 45.
```
## MCP Client Configuration
<details>
<summary><b>Claude Desktop</b></summary>
Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or equivalent:
**Public Spaces:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-space.hf.space/gradio_api/mcp/sse"
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-private-space.hf.space/gradio_api/mcp/sse",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"url": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
```
</details>
<details>
<summary><b>Claude Code</b></summary>
See [Claude Code MCP docs](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/tutorials#set-up-model-context-protocol-mcp) for more info.
**Public Spaces:**
```sh
claude mcp add --transport sse trackio https://your-space.hf.space/gradio_api/mcp/sse
```
**Private Spaces/Datasets:**
```sh
claude mcp add --transport sse --header "Authorization: Bearer YOUR_HF_TOKEN" trackio https://your-private-space.hf.space/gradio_api/mcp/sse
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"type": "sse",
"url": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
```
</details>
<details>
<summary><b>Cursor</b></summary>
Add to your Cursor `~/.cursor/mcp.json` file or create `.cursor/mcp.json` in your project folder. See [Cursor MCP docs](https://docs.cursor.com/context/model-context-protocol) for more info.
**Public Spaces:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-space.hf.space/gradio_api/mcp/sse"
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-private-space.hf.space/gradio_api/mcp/sse",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"url": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
```
</details>
<details>
<summary><b>Windsurf</b></summary>
Add to your Windsurf MCP config file. See [Windsurf MCP docs](https://docs.windsurf.com/windsurf/mcp) for more info.
**Public Spaces:**
```json
{
"mcpServers": {
"trackio": {
"serverUrl": "https://your-space.hf.space/gradio_api/mcp/sse"
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcpServers": {
"trackio": {
"serverUrl": "https://your-private-space.hf.space/gradio_api/mcp/sse",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"serverUrl": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
```
</details>
<details>
<summary><b>VS Code</b></summary>
Add to `.vscode/mcp.json`. See [VS Code MCP docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more info.
**Public Spaces:**
```json
{
"mcp": {
"servers": {
"trackio": {
"type": "http",
"url": "https://your-space.hf.space/gradio_api/mcp/sse"
}
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcp": {
"servers": {
"trackio": {
"type": "http",
"url": "https://your-private-space.hf.space/gradio_api/mcp/sse",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}
}
```
**Local Development:**
```json
{
"mcp": {
"servers": {
"trackio": {
"type": "http",
"url": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
}
```
</details>
<details>
<summary><b>Gemini CLI</b></summary>
Add to `mcp.json` in your project directory. See [Gemini CLI Configuration](https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/configuration.md) for details.
**Public Spaces:**
```json
{
"mcpServers": {
"trackio": {
"command": "npx",
"args": ["mcp-remote", "https://your-space.hf.space/gradio_api/mcp/sse"]
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcpServers": {
"trackio": {
"command": "npx",
"args": ["mcp-remote", "https://your-private-space.hf.space/gradio_api/mcp/sse"],
"env": {
"HF_TOKEN": "YOUR_HF_TOKEN"
}
}
}
}
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:7860/gradio_api/mcp/sse"]
}
}
}
```
</details>
<details>
<summary><b>Cline</b></summary>
Create `.cursor/mcp.json` (or equivalent for your IDE):
**Public Spaces:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-space.hf.space/gradio_api/mcp/sse"
}
}
}
```
**Private Spaces/Datasets:**
```json
{
"mcpServers": {
"trackio": {
"url": "https://your-private-space.hf.space/gradio_api/mcp/sse",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}
```
**Local Development:**
```json
{
"mcpServers": {
"trackio": {
"url": "http://localhost:7860/gradio_api/mcp/sse"
}
}
}
```
</details>
## Configuration
### Environment Variables
- `TRACKIO_DISABLE_MCP`: Set to `"true"` to disable MCP functionality (default: MCP enabled)
### Programmatic Control
```python
import os
os.environ["TRACKIO_DISABLE_MCP"] = "true" # Disable MCP
import trackio_mcp # MCP won't be enabled
import trackio
```
## How It Works
`trackio-mcp` uses monkey-patching to automatically:
1. **Enable MCP server**: Sets `mcp_server=True` on all Gradio launches
2. **Enable API**: Sets `show_api=True` to expose Gradio API endpoints
3. **Add tools**: Registers additional trackio-specific MCP tools
4. **Preserve compatibility**: No changes needed to existing trackio code
The package patches:
- `gradio.Blocks.launch()` - Core Gradio launch method
- `trackio.ui.demo.launch()` - Trackio dashboard launches
- Adds new MCP endpoints at `/gradio_api/mcp/sse`
## Deployment Examples
### Local Development
```python
import trackio_mcp
import trackio
# Start local tracking with MCP enabled
trackio.show() # Dashboard + MCP server at http://localhost:7860
```
### Public Spaces Deployment
```python
import trackio_mcp
import trackio as wandb
# Deploy to public Spaces with MCP support
wandb.init(
project="public-model",
space_id="username/model-tracking"
)
wandb.log({"epoch": 1, "loss": 0.5})
wandb.finish()
```
### Private Spaces/Datasets Deployment
```python
import trackio_mcp
import trackio as wandb
# Deploy to private Spaces with private dataset
wandb.init(
project="private-model",
space_id="organization/private-model-tracking", # Private space
dataset_id="organization/private-model-metrics" # Private dataset
)
wandb.log({"epoch": 1, "loss": 0.5})
wandb.finish()
```
## CLI Interface
```bash
# Launch standalone MCP server
trackio-mcp server --port 7861
# Check status and configuration
trackio-mcp status
# Test MCP server functionality
trackio-mcp test --url http://localhost:7860
```
## Security Considerations
- **Private Spaces**: Use HF tokens for authentication with private spaces/datasets
- **Access Control**: MCP server inherits trackio's access controls
- **Network Security**: Consider firewall rules for production deployments
- **Token Management**: Store HF tokens securely, use environment variables
## Troubleshooting
### MCP Server Not Available
```python
import trackio_mcp
import trackio
# Check if MCP was disabled
import os
print("MCP Disabled:", os.getenv("TRACKIO_DISABLE_MCP"))
# Manual verification
trackio.show() # Look for MCP server URL in output
```
### Connection Issues
1. **Check URL**: Ensure correct `/gradio_api/mcp/sse` endpoint
2. **Authentication**: Add Bearer token for private Spaces/datasets
3. **Network**: Verify firewall/proxy settings
4. **Dependencies**: Ensure `gradio[mcp]` is installed
### Tool Discovery Issues
```python
# Test tools manually
from trackio_mcp.tools import register_trackio_tools
tools = register_trackio_tools()
tools.launch(mcp_server=True) # Test tools interface
```
## Contributing
1. Fork the repository
2. Install development dependencies: `pip install -e .[dev]`
3. Make your changes
4. Run tests: `pytest`
5. Submit a pull request
## License
MIT License - see [LICENSE](LICENSE) file.
## Acknowledgments
- [trackio](https://github.com/gradio-app/trackio) - The excellent experiment tracking library
- [Gradio](https://gradio.app) - For built-in MCP server support
- [Model Context Protocol](https://modelcontextprotocol.io) - For the standardized AI tool protocol
---
**Made with care for the AI research community**
Raw data
{
"_id": null,
"home_page": null,
"name": "trackio-mcp",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "AI agents, MCP, Model Context Protocol, experiment tracking, gradio, machine learning, trackio",
"author": "Fatih Akyon",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/cf/14/bf27a169898618de554a346771cd67bbddf971f6f4b3b9cfeec76d9da7d4/trackio_mcp-0.2.0.tar.gz",
"platform": null,
"description": "# trackio-mcp\n\n[](https://badge.fury.io/py/trackio-mcp)\n[](https://opensource.org/licenses/MIT)\n[](https://github.com/fcakyon/trackio-mcp/actions)\n\n**MCP (Model Context Protocol) server support for trackio experiment tracking**\n\nThis package enables AI agents to observe and interact with [trackio](https://github.com/gradio-app/trackio) experiments through the Model Context Protocol (MCP). Simply import `trackio_mcp` before `trackio` to automatically enable MCP server functionality.\n\n## Features\n\n- **Zero-code integration**: Just import `trackio_mcp` before `trackio` \n- **Automatic MCP server**: Enables MCP server on all trackio deployments (local & Spaces)\n- **Rich tool set**: Exposes trackio functionality as MCP tools for AI agents\n- **Spaces compatible**: Works seamlessly with Hugging Face Spaces deployments\n- **Drop-in replacement**: No changes needed to existing trackio code\n\n## Installation\n\n```bash\npip install trackio-mcp\n```\n\nOr with development dependencies:\n\n```bash\npip install trackio-mcp[dev]\n```\n\n## Quick Start\n\n### Basic Usage\n\nSimply import `trackio_mcp` before importing `trackio`:\n\n```python\nimport trackio_mcp # This enables MCP server functionality\nimport trackio as wandb\n\n# Your existing trackio code works unchanged\nwandb.init(project=\"my-experiment\")\nwandb.log({\"loss\": 0.1, \"accuracy\": 0.95})\nwandb.finish()\n```\n\nThe MCP server will be automatically available at:\n- **Local**: `http://localhost:7860/gradio_api/mcp/sse` \n- **Spaces**: `https://your-space.hf.space/gradio_api/mcp/sse`\n\n### Deploy to Hugging Face Spaces with MCP\n\n```python\nimport trackio_mcp\nimport trackio as wandb\n\n# Deploy to Spaces with MCP enabled automatically\nwandb.init(\n project=\"my-experiment\", \n space_id=\"username/my-trackio-space\"\n)\n\nwandb.log({\"loss\": 0.1})\nwandb.finish()\n```\n\n### Standalone MCP Server\n\nLaunch a dedicated MCP server for trackio tools:\n\n```python\nfrom trackio_mcp.tools import launch_trackio_mcp_server\n\n# Launch standalone MCP server on port 7861\nlaunch_trackio_mcp_server(port=7861, share=False)\n```\n\n## Available MCP Tools\n\nOnce connected, AI agents can use these trackio tools:\n\n### Core Tools (via Gradio API)\n- **log**: Log metrics to a trackio run\n- **upload_db_to_space**: Upload local database to a Space\n\n### Extended Tools (via trackio-mcp)\n- **get_projects**: List all trackio projects\n- **get_runs**: Get runs for a specific project \n- **filter_runs**: Filter runs by name pattern\n- **get_run_metrics**: Get metrics data for a specific run\n- **get_available_metrics**: Get all available metric names for a project\n- **load_run_data**: Load and process run data with optional smoothing\n- **get_project_summary**: Get comprehensive project statistics\n\n### Example Agent Interaction\n\n```\nHuman: \"Show me the latest results from my 'image-classification' project\"\n\nAgent: I'll check your trackio projects and get the latest results.\n\n[Tool: get_projects] \u2192 finds \"image-classification\" project\n[Tool: get_runs] \u2192 gets runs for \"image-classification\" \n[Tool: get_run_metrics] \u2192 gets metrics for latest run\n[Tool: get_available_metrics] \u2192 gets metric names\n\nAgent: Your latest image-classification run achieved 94.2% accuracy with a final loss of 0.18. The model trained for 50 epochs with best validation accuracy of 94.7% at epoch 45.\n```\n\n## MCP Client Configuration\n\n<details>\n<summary><b>Claude Desktop</b></summary>\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or equivalent:\n\n**Public Spaces:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-space.hf.space/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-private-space.hf.space/gradio_api/mcp/sse\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_HF_TOKEN\"\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Claude Code</b></summary>\n\nSee [Claude Code MCP docs](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/tutorials#set-up-model-context-protocol-mcp) for more info.\n\n**Public Spaces:**\n```sh\nclaude mcp add --transport sse trackio https://your-space.hf.space/gradio_api/mcp/sse\n```\n\n**Private Spaces/Datasets:**\n```sh\nclaude mcp add --transport sse --header \"Authorization: Bearer YOUR_HF_TOKEN\" trackio https://your-private-space.hf.space/gradio_api/mcp/sse\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"type\": \"sse\",\n \"url\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Cursor</b></summary>\n\nAdd to your Cursor `~/.cursor/mcp.json` file or create `.cursor/mcp.json` in your project folder. See [Cursor MCP docs](https://docs.cursor.com/context/model-context-protocol) for more info.\n\n**Public Spaces:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-space.hf.space/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-private-space.hf.space/gradio_api/mcp/sse\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_HF_TOKEN\"\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Windsurf</b></summary>\n\nAdd to your Windsurf MCP config file. See [Windsurf MCP docs](https://docs.windsurf.com/windsurf/mcp) for more info.\n\n**Public Spaces:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"serverUrl\": \"https://your-space.hf.space/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"serverUrl\": \"https://your-private-space.hf.space/gradio_api/mcp/sse\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_HF_TOKEN\"\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"serverUrl\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>VS Code</b></summary>\n\nAdd to `.vscode/mcp.json`. See [VS Code MCP docs](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) for more info.\n\n**Public Spaces:**\n```json\n{\n \"mcp\": {\n \"servers\": {\n \"trackio\": {\n \"type\": \"http\",\n \"url\": \"https://your-space.hf.space/gradio_api/mcp/sse\"\n }\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcp\": {\n \"servers\": {\n \"trackio\": {\n \"type\": \"http\", \n \"url\": \"https://your-private-space.hf.space/gradio_api/mcp/sse\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_HF_TOKEN\"\n }\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcp\": {\n \"servers\": {\n \"trackio\": {\n \"type\": \"http\",\n \"url\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Gemini CLI</b></summary>\n\nAdd to `mcp.json` in your project directory. See [Gemini CLI Configuration](https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/configuration.md) for details.\n\n**Public Spaces:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"command\": \"npx\",\n \"args\": [\"mcp-remote\", \"https://your-space.hf.space/gradio_api/mcp/sse\"]\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"command\": \"npx\", \n \"args\": [\"mcp-remote\", \"https://your-private-space.hf.space/gradio_api/mcp/sse\"],\n \"env\": {\n \"HF_TOKEN\": \"YOUR_HF_TOKEN\"\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"command\": \"npx\",\n \"args\": [\"mcp-remote\", \"http://localhost:7860/gradio_api/mcp/sse\"]\n }\n }\n}\n```\n\n</details>\n\n<details>\n<summary><b>Cline</b></summary>\n\nCreate `.cursor/mcp.json` (or equivalent for your IDE):\n\n**Public Spaces:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-space.hf.space/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n**Private Spaces/Datasets:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"https://your-private-space.hf.space/gradio_api/mcp/sse\",\n \"headers\": {\n \"Authorization\": \"Bearer YOUR_HF_TOKEN\"\n }\n }\n }\n}\n```\n\n**Local Development:**\n```json\n{\n \"mcpServers\": {\n \"trackio\": {\n \"url\": \"http://localhost:7860/gradio_api/mcp/sse\"\n }\n }\n}\n```\n\n</details>\n\n## Configuration\n\n### Environment Variables\n\n- `TRACKIO_DISABLE_MCP`: Set to `\"true\"` to disable MCP functionality (default: MCP enabled)\n\n### Programmatic Control\n\n```python\nimport os\nos.environ[\"TRACKIO_DISABLE_MCP\"] = \"true\" # Disable MCP\nimport trackio_mcp # MCP won't be enabled\nimport trackio\n```\n\n## How It Works\n\n`trackio-mcp` uses monkey-patching to automatically:\n\n1. **Enable MCP server**: Sets `mcp_server=True` on all Gradio launches\n2. **Enable API**: Sets `show_api=True` to expose Gradio API endpoints \n3. **Add tools**: Registers additional trackio-specific MCP tools\n4. **Preserve compatibility**: No changes needed to existing trackio code\n\nThe package patches:\n- `gradio.Blocks.launch()` - Core Gradio launch method\n- `trackio.ui.demo.launch()` - Trackio dashboard launches\n- Adds new MCP endpoints at `/gradio_api/mcp/sse`\n\n## Deployment Examples\n\n### Local Development\n\n```python\nimport trackio_mcp\nimport trackio\n\n# Start local tracking with MCP enabled\ntrackio.show() # Dashboard + MCP server at http://localhost:7860\n```\n\n### Public Spaces Deployment\n\n```python\nimport trackio_mcp\nimport trackio as wandb\n\n# Deploy to public Spaces with MCP support\nwandb.init(\n project=\"public-model\",\n space_id=\"username/model-tracking\"\n)\n\nwandb.log({\"epoch\": 1, \"loss\": 0.5})\nwandb.finish()\n```\n\n### Private Spaces/Datasets Deployment\n\n```python\nimport trackio_mcp\nimport trackio as wandb\n\n# Deploy to private Spaces with private dataset\nwandb.init(\n project=\"private-model\",\n space_id=\"organization/private-model-tracking\", # Private space\n dataset_id=\"organization/private-model-metrics\" # Private dataset\n)\n\nwandb.log({\"epoch\": 1, \"loss\": 0.5})\nwandb.finish()\n```\n\n## CLI Interface\n\n```bash\n# Launch standalone MCP server\ntrackio-mcp server --port 7861\n\n# Check status and configuration\ntrackio-mcp status\n\n# Test MCP server functionality\ntrackio-mcp test --url http://localhost:7860\n```\n\n## Security Considerations\n\n- **Private Spaces**: Use HF tokens for authentication with private spaces/datasets\n- **Access Control**: MCP server inherits trackio's access controls\n- **Network Security**: Consider firewall rules for production deployments\n- **Token Management**: Store HF tokens securely, use environment variables\n\n## Troubleshooting\n\n### MCP Server Not Available\n\n```python\nimport trackio_mcp\nimport trackio\n\n# Check if MCP was disabled\nimport os\nprint(\"MCP Disabled:\", os.getenv(\"TRACKIO_DISABLE_MCP\"))\n\n# Manual verification\ntrackio.show() # Look for MCP server URL in output\n```\n\n### Connection Issues\n\n1. **Check URL**: Ensure correct `/gradio_api/mcp/sse` endpoint\n2. **Authentication**: Add Bearer token for private Spaces/datasets\n3. **Network**: Verify firewall/proxy settings\n4. **Dependencies**: Ensure `gradio[mcp]` is installed\n\n### Tool Discovery Issues\n\n```python\n# Test tools manually\nfrom trackio_mcp.tools import register_trackio_tools\n\ntools = register_trackio_tools()\ntools.launch(mcp_server=True) # Test tools interface\n```\n\n## Contributing\n\n1. Fork the repository\n2. Install development dependencies: `pip install -e .[dev]`\n3. Make your changes\n4. Run tests: `pytest`\n5. Submit a pull request\n\n## License\n\nMIT License - see [LICENSE](LICENSE) file.\n\n## Acknowledgments\n\n- [trackio](https://github.com/gradio-app/trackio) - The excellent experiment tracking library\n- [Gradio](https://gradio.app) - For built-in MCP server support\n- [Model Context Protocol](https://modelcontextprotocol.io) - For the standardized AI tool protocol\n\n---\n\n**Made with care for the AI research community**",
"bugtrack_url": null,
"license": null,
"summary": "MCP (Model Context Protocol) server support for trackio experiment tracking",
"version": "0.2.0",
"project_urls": {
"documentation": "https://github.com/fcakyon/trackio-mcp#readme",
"homepage": "https://github.com/fcakyon/trackio-mcp",
"issues": "https://github.com/fcakyon/trackio-mcp/issues",
"repository": "https://github.com/fcakyon/trackio-mcp"
},
"split_keywords": [
"ai agents",
" mcp",
" model context protocol",
" experiment tracking",
" gradio",
" machine learning",
" trackio"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "df1a7faf842e4b8a3b79636d9ff7b6ecbe0b330937a84b439a77f140c3fffd64",
"md5": "e7017b1677962bf51e702c3d47fe9906",
"sha256": "6e518a098cc7ab3ae24076cf3c563f8e4564c0b72b3c621505d5209ec1fc4a58"
},
"downloads": -1,
"filename": "trackio_mcp-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "e7017b1677962bf51e702c3d47fe9906",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 11867,
"upload_time": "2025-08-03T13:37:45",
"upload_time_iso_8601": "2025-08-03T13:37:45.683726Z",
"url": "https://files.pythonhosted.org/packages/df/1a/7faf842e4b8a3b79636d9ff7b6ecbe0b330937a84b439a77f140c3fffd64/trackio_mcp-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "cf14bf27a169898618de554a346771cd67bbddf971f6f4b3b9cfeec76d9da7d4",
"md5": "9fb194fd0adc49b3181fc47cdd86aaa3",
"sha256": "ebed6dd38d4346ad58f6743d3ddc5ed688f701aefac3e8dcc5d2e18471603f8a"
},
"downloads": -1,
"filename": "trackio_mcp-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "9fb194fd0adc49b3181fc47cdd86aaa3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 15758,
"upload_time": "2025-08-03T13:37:47",
"upload_time_iso_8601": "2025-08-03T13:37:47.065565Z",
"url": "https://files.pythonhosted.org/packages/cf/14/bf27a169898618de554a346771cd67bbddf971f6f4b3b9cfeec76d9da7d4/trackio_mcp-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-03 13:37:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "fcakyon",
"github_project": "trackio-mcp#readme",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "trackio-mcp"
}
JSON
