feat: Add URL and Gradio file handling to tools and include sample heart.csv dataset.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.csv filter=lfs diff=lfs merge=lfs -text

README.md

@@ -59,3 +59,38 @@ You can now connect any MCP-compliant client (e.g., Claude Desktop) to this serv
 1.  Upload a CSV file.
 2.  Specify a target column.
 3.  Receive a deployed API URL for the trained model.
+
+## Client Configuration
+
+To enable your AI agent to upload local files to this server, you can add the following tool definition to your MCP client configuration (e.g., `claude_desktop_config.json`).
+
+**Note**: This tool requires `uv` to be installed on your local machine.
+
+```json
+{
+  "mcpServers": {
+    "auto-deployer": {
+      "command": "uvx",
+      "args": [
+        "gradio",
+        "mcp",
+        "https://mcp-1st-birthday-auto-deployer.hf.space/gradio_api/mcp/"
+      ]
+    },
+    "upload_files_to_gradio": {
+      "command": "uvx",
+      "args": [
+        "--from",
+        "gradio[mcp]",
+        "gradio",
+        "upload-mcp",
+        "https://mcp-1st-birthday-auto-deployer.hf.space",
+        "./upload_files"
+      ]
+    }
+  }
+}
+```
+
+### Tool Description
+The `upload_files_to_gradio` tool uploads files from your local `<UPLOAD_DIRECTORY>` (or any of its subdirectories) to the Gradio app. This is needed because MCP servers require files to be provided as URLs. You can omit this tool if you prefer to upload files manually.

app.py

@@ -1,9 +1,12 @@
-import gradio as gr
-import modal
 import json
 import subprocess
 import sys
 import os
+import requests
+
+import gradio as gr
+import modal
+
 
 def check_modal_backend_running():
     """
@@ -18,12 +21,13 @@ def check_modal_backend_running():
             ["modal", "app", "list", "--json"],
             capture_output=True,
             text=True,
-            timeout=30
+            timeout=30,
         )
 
         if result.returncode == 0:
             # Parse the JSON output to check if mlops-backend is running
             import json
+
             apps = json.loads(result.stdout)
             for app in apps:
                 if app.get("name") == "mlops-backend" and app.get("state") == "ready":
@@ -40,6 +44,7 @@ def check_modal_backend_running():
         print(f"Error checking Modal backend status: {e}")
         return False
 
+
 def deploy_modal_backend():
     """
     Deploy the Modal backend if it's not already running.
@@ -58,7 +63,7 @@ def deploy_modal_backend():
             ["modal", "deploy", "modal_backend.py"],
             capture_output=True,
             text=True,
-            timeout=300  # 5 minutes timeout
+            timeout=300,  # 5 minutes timeout
         )
 
         if result.returncode == 0:
@@ -75,32 +80,59 @@ def deploy_modal_backend():
         print(f"❌ Error deploying Modal backend: {e}")
         return False
 
+
 # Initialize Modal function references
 f_analyze = modal.Function.from_name("mlops-backend", "analyze_data")
 f_train = modal.Function.from_name("mlops-backend", "train_model")
 f_check = modal.Function.from_name("mlops-backend", "check_model")
 
+
+def get_file_content(file_path: str) -> str:
+    """
+    Retrieves content from a file path or URL.
+    Handles Gradio file URLs by extracting the local path if possible.
+    """
+    if file_path.startswith("http://") or file_path.startswith("https://"):
+        # Try to extract local path from Gradio file URL
+        if "/file=" in file_path:
+            local_path = file_path.split("/file=")[1]
+            if os.path.exists(local_path):
+                with open(local_path, "r") as f:
+                    return f.read()
+        
+        # Download from URL
+        print(f"Downloading file from: {file_path}")
+        response = requests.get(file_path)
+        response.raise_for_status()
+        return response.text
+        
+    with open(file_path, "r") as f:
+        return f.read()
+
+
 def analyze_data_tool(file_path: str) -> str:
     """
     Analyzes the uploaded CSV file and returns statistical metadata.
-    
+
     Args:
         file_path: The path to the uploaded CSV file.
     Returns:
         str: JSON string with analysis results.
     """
-    with open(file_path, "r") as f:
-        content = f.read()
-        
+    content = get_file_content(file_path)
+
     # Call Modal backend
     result = f_analyze.remote(content)
-    
+
     return json.dumps(result, indent=2)
 
-def train_model_tool(file_path: str, target_column: str, task_type: str = "classification") -> str:
+
+def train_model_tool(
+    file_path: str, target_column: str, task_type: str = "classification"
+) -> str:
     """
     Trains a model on the uploaded CSV file.
-    
+
     Args:
         file_path: The path to the uploaded CSV file.
         target_column: The name of the column to predict.
@@ -108,22 +140,25 @@ def train_model_tool(file_path: str, target_column: str, task_type: str = "class
     Returns:
         str: JSON string with training results.
     """
-    with open(file_path, "r") as f:
-        content = f.read()
-        
+    content = get_file_content(file_path)
+
     # Call Modal backend
     result = f_train.remote(content, target_column, task_type)
-    
-    return json.dumps({
-        "message": result['message'],
-        "model_id": result['model_id'],
-        "metric": f"{result['metric_name']}: {result['metric_value']:.4f}"
-    }, indent=2)
+
+    return json.dumps(
+        {
+            "message": result["message"],
+            "model_id": result["model_id"],
+            "metric": f"{result['metric_name']}: {result['metric_value']:.4f}",
+        },
+        indent=2,
+    )
+
 
 def deploy_model_tool(model_id: str) -> str:
     """
     Deploys a trained model and returns the API usage code.
-    
+
     Args:
         model_id: The ID of the model to deploy.
     Returns:
@@ -131,12 +166,12 @@ def deploy_model_tool(model_id: str) -> str:
     """
     # Verify model exists
     check = f_check.remote(model_id)
-    if not check['exists']:
+    if not check["exists"]:
         return f"Error: Model {model_id} not found."
 
     # Construct the API usage example
-    api_url = "https://abidali899--mlops-backend-predict-api.modal.run" 
-    
+    api_url = "https://abidali899--mlops-backend-predict-api.modal.run"
+
     usage_code = f"""
 import requests
 
@@ -148,7 +183,7 @@ payload = {{
 response = requests.post(url, json=payload)
 print(response.json())
     """
-    
+
     curl_code = f"""
 curl -X POST {api_url} \\
 -H "Content-Type: application/json" \\
@@ -157,13 +192,16 @@ curl -X POST {api_url} \\
     "data": {{ "col1": "val1", "col2": "val2" }}
 }}'
     """
-    
+
     return f"Model {model_id} is live!\n\nEndpoint: {api_url}\n\n### Usage (Python):\n```python\n{usage_code}\n```\n\n### Usage (cURL):\n```bash\n{curl_code}\n```"
 
-def auto_deploy_tool(file_path: str, target_column: str, task_type: str = "classification") -> str:
+
+def auto_deploy_tool(
+    file_path: str, target_column: str, task_type: str = "classification"
+) -> str:
     """
     Full Pipeline: Analyzes data, trains model, evaluates, and deploys it in one go.
-    
+
     Args:
         file_path: The path to the uploaded CSV file.
         target_column: The name of the column to predict.
@@ -171,21 +209,20 @@ def auto_deploy_tool(file_path: str, target_column: str, task_type: str = "class
     Returns:
         str: A detailed report of the pipeline execution.
     """
-    with open(file_path, "r") as f:
-        content = f.read()
-    
+    content = get_file_content(file_path)
+
     # 1. Analyze
     analysis = f_analyze.remote(content)
-    
+
     # 2. Train & Evaluate
     train_result = f_train.remote(content, target_column, task_type)
-    model_id = train_result['model_id']
-    metric_val = train_result['metric_value']
-    metric_name = train_result['metric_name']
-    
+    model_id = train_result["model_id"]
+    metric_val = train_result["metric_value"]
+    metric_name = train_result["metric_name"]
+
     # 3. Deploy (Construct Info)
     api_url = "https://abidali899--mlops-backend-predict-api.modal.run"
-    
+
     usage_code = f"""
 import requests
 
@@ -206,12 +243,12 @@ curl -X POST {api_url} \\
     "data": {{ "col1": "val1", "col2": "val2" }}
 }}'
     """
-    
+
     report = f"""# Auto-Deployment Report
 
 ## 1. Data Analysis
-- **Shape**: {analysis['shape']}
-- **Columns**: {', '.join(analysis['columns'])}
+- **Shape**: {analysis["shape"]}
+- **Columns**: {", ".join(analysis["columns"])}
 
 ## 2. Model Training
 - **Task**: {task_type}
@@ -233,6 +270,7 @@ The model is live at: `{api_url}`
 """
     return report
 
+
 with gr.Blocks() as demo:
     gr.Markdown("# Auto-Deployer MCP Server")
     gr.Markdown("This server exposes the following tools to MCP clients:")
@@ -240,15 +278,9 @@ with gr.Blocks() as demo:
     gr.Markdown("- `train_model_tool`")
     gr.Markdown("- `deploy_model_tool`")
     gr.Markdown("- `auto_deploy_tool`")
-    
-    # # Register tools using gr.api
-    # gr.api(analyze_data_tool)
-    # gr.api(train_model_tool)
-    # gr.api(deploy_model_tool)
-    # gr.api(auto_deploy_tool)
 
     gr.Markdown("## Manual Testing Interface")
-    
+
     with gr.Tab("Analyze"):
         an_file = gr.File(label="CSV File")
         an_btn = gr.Button("Analyze Data")
@@ -258,7 +290,11 @@ with gr.Blocks() as demo:
     with gr.Tab("Train"):
         t_file = gr.File(label="CSV File")
         t_col = gr.Textbox(label="Target Column")
-        t_type = gr.Dropdown(["classification", "regression", "time_series"], label="Task Type", value="classification")
+        t_type = gr.Dropdown(
+            ["classification", "regression", "time_series"],
+            label="Task Type",
+            value="classification",
+        )
         t_btn = gr.Button("Train")
         t_out = gr.JSON(label="Output")
         t_btn.click(train_model_tool, [t_file, t_col, t_type], t_out)
@@ -272,7 +308,11 @@ with gr.Blocks() as demo:
     with gr.Tab("Auto Deploy"):
         a_file = gr.File(label="CSV File")
         a_col = gr.Textbox(label="Target Column")
-        a_type = gr.Dropdown(["classification", "regression", "time_series"], label="Task Type", value="classification")
+        a_type = gr.Dropdown(
+            ["classification", "regression", "time_series"],
+            label="Task Type",
+            value="classification",
+        )
         a_btn = gr.Button("Auto Deploy")
         a_out = gr.Markdown(label="Output")
         a_btn.click(auto_deploy_tool, [a_file, a_col, a_type], a_out)
@@ -288,5 +328,3 @@ if __name__ == "__main__":
         sys.exit(1)
 
     demo.launch(mcp_server=True)
-
-

upload_files/heart.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948420b084d8a3a0ca42b8419fce9aee175879e43f8aedf712377899a67aa49b
+size 35921