tracktion-engine-mcp
README.md
# Tracktion Engine MCP
An MCP (Model Context Protocol) server that provides AI assistants with access to Tracktion Engine API documentation.
## Installation
```bash
npm install
npm run setup # Clones Tracktion Engine and parses headers
npm run build
```
## Usage with Claude Code
Add to your Claude Code MCP settings:
```json
{
"mcpServers": {
"tracktion-engine": {
"command": "node",
"args": ["/path/to/tracktion-engine-mcp/dist/index.js"]
}
}
}
```
## Tools
### `search_te_classes`
Search for Tracktion Engine classes by name or description.
```
query: "track"
limit: 10
```
### `get_te_class_docs`
Get detailed documentation for a specific class.
```
className: "AudioTrack"
```
## Development
```bash
npm run dev # Run with tsx (no build needed)
npm run parse-headers # Re-parse TE headers
npm run build # Build for production
```
## Updating API Data
To update the API documentation after Tracktion Engine updates:
```bash
cd tracktion_engine && git pull
cd .. && npm run parse-headers
```
## License
MIT
TDQS
A3.5/5.0
Scored across 2 tools
Disambiguation5/5
Search and get-docs are clearly distinct operations: one discovers classes via query, the other retrieves detailed documentation for a specific class. No overlap or ambiguity.
Naming Consistency5/5
Both tool names follow a consistent verb_noun pattern with the 'te' prefix (search_te_classes, get_te_class_docs), making the naming uniform and predictable.
Tool Count3/5
Two tools is minimal but defensible for a focused documentation lookup server. It feels slightly thin, but the pair covers the essential search-and-retrieve workflow.
Completeness4/5
The search and get-docs pair forms a complete workflow for browsing class documentation. No critical operations like listing or cross-referencing are obviously required for the stated purpose.
Maintenance
ActivityInactive
ResponsivenessNo issues