read_backtest_chart
Retrieve and analyze chart data from specific backtests on QuantConnect. Use the tool to access historical performance metrics, set time ranges, and extract key insights for strategy evaluation.
Instructions
Read chart data from a backtest.
Args: project_id: Project ID containing the backtest backtest_id: ID of the backtest to get chart from name: Name of the chart to retrieve (e.g., "Strategy Equity") count: Number of data points to request (default: 100) start: Optional UTC start timestamp in seconds end: Optional UTC end timestamp in seconds
Returns: Dictionary containing chart data or loading status
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| backtest_id | Yes | ||
| count | No | ||
| end | No | ||
| name | Yes | ||
| project_id | Yes | ||
| start | No |
Implementation Reference
- The core handler function for the 'read_backtest_chart' tool. It authenticates with QuantConnect, prepares the request with project_id, backtest_id, chart name, count, and optional timestamps, calls the 'backtests/chart/read' API endpoint, and returns chart data or loading progress.@mcp.tool() async def read_backtest_chart( project_id: int, backtest_id: str, name: str, count: int = 100, start: Optional[int] = None, end: Optional[int] = None, ) -> Dict[str, Any]: """ Read chart data from a backtest. Args: project_id: Project ID containing the backtest backtest_id: ID of the backtest to get chart from name: Name of the chart to retrieve (e.g., "Strategy Equity") count: Number of data points to request (default: 100) start: Optional UTC start timestamp in seconds end: Optional UTC end timestamp in seconds Returns: Dictionary containing chart data or loading status """ auth = get_auth_instance() if auth is None: return { "status": "error", "error": "QuantConnect authentication not configured. Use configure_auth() first.", } try: # Prepare request data request_data = { "projectId": project_id, "backtestId": backtest_id, "name": name, "count": count, } # Add optional timestamp parameters if start is not None: request_data["start"] = start if end is not None: request_data["end"] = end # Make API request response = await auth.make_authenticated_request( endpoint="backtests/chart/read", method="POST", json=request_data ) # Parse response if response.status_code == 200: data = response.json() if data.get("success", False): # Check if chart is still loading if "progress" in data and "status" in data: progress = data.get("progress", 0) status = data.get("status", "loading") return { "status": "loading", "project_id": project_id, "backtest_id": backtest_id, "chart_name": name, "progress": progress, "chart_status": status, "message": f"Chart '{name}' is loading... ({progress * 100:.1f}% complete)", } # Chart is ready elif "chart" in data: chart = data.get("chart") return { "status": "success", "project_id": project_id, "backtest_id": backtest_id, "chart_name": name, "chart": chart, "count": count, "start": start, "end": end, "message": f"Successfully retrieved chart '{name}' from backtest {backtest_id}", } else: return { "status": "error", "error": "Unexpected response format - no chart or progress data found", } else: # API returned success=false errors = data.get("errors", ["Unknown error"]) return { "status": "error", "error": "Failed to read backtest chart", "details": errors, "project_id": project_id, "backtest_id": backtest_id, "chart_name": name, } elif response.status_code == 401: return { "status": "error", "error": "Authentication failed. Check your credentials and ensure they haven't expired.", } else: return { "status": "error", "error": f"API request failed with status {response.status_code}", "response_text": ( response.text[:500] if hasattr(response, "text") else "No response text" ), } except Exception as e: return { "status": "error", "error": f"Failed to read backtest chart: {str(e)}", "project_id": project_id, "backtest_id": backtest_id, "chart_name": name, }
- quantconnect_mcp/src/server.py:76-79 (registration)Registration of backtest tools (including read_backtest_chart) by calling register_backtest_tools(mcp) during server initialization.register_file_tools(mcp) register_backtest_tools(mcp) register_live_tools(mcp) register_optimization_tools(mcp)
- quantconnect_mcp/main.py:49-52 (registration)Alternative entry point registration of backtest tools (including read_backtest_chart) by calling register_backtest_tools(mcp).register_file_tools(mcp) register_backtest_tools(mcp) register_live_tools(mcp) register_optimization_tools(mcp)