content-core 1.0.4__py3-none-any.whl → 1.1.0__py3-none-any.whl

content_core/config.py

@@ -1,6 +1,5 @@
 import os
 import pkgutil
-import os  # needed for load_config env/path checks
 import yaml
 from dotenv import load_dotenv
 

content_core/mcp/__init__.py

@@ -0,0 +1,5 @@
+"""Content Core MCP Server module."""
+
+from .server import mcp, main
+
+__all__ = ["mcp", "main"]

content_core/mcp/server.py

@@ -0,0 +1,211 @@
+"""Content Core MCP Server implementation."""
+
+import os
+import sys
+from contextlib import contextmanager
+from datetime import datetime
+from io import StringIO
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+from fastmcp import FastMCP
+from loguru import logger
+
+# Suppress MoviePy output for MCP compatibility
+os.environ["IMAGEIO_LOG_LEVEL"] = "error"
+os.environ["FFMPEG_LOG_LEVEL"] = "error"
+
+# Configure loguru to not output to stdout (which would interfere with MCP)
+logger.remove()  # Remove default handler
+logger.add(sys.stderr, level="INFO")  # Add stderr handler only
+
+
+@contextmanager
+def suppress_stdout():
+    """Context manager to suppress stdout during operations that might print."""
+    original_stdout = sys.stdout
+    sys.stdout = StringIO()
+    try:
+        yield
+    finally:
+        sys.stdout = original_stdout
+
+# Add parent directory to path to import content_core
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(__file__))))
+
+import content_core as cc
+
+# Initialize MCP server
+mcp = FastMCP("Content Core MCP Server")
+
+async def _extract_content_impl(
+    url: Optional[str] = None,
+    file_path: Optional[str] = None
+) -> Dict[str, Any]:
+    """
+    Extract content from a URL or file using Content Core's auto engine.
+    
+    Args:
+        url: Optional URL to extract content from
+        file_path: Optional file path to extract content from
+        
+    Returns:
+        JSON object containing extracted content and metadata
+        
+    Raises:
+        ValueError: If neither or both url and file_path are provided
+    """
+    # Validate input - exactly one must be provided
+    if (url is None and file_path is None) or (url is not None and file_path is not None):
+        return {
+            "success": False,
+            "error": "Exactly one of 'url' or 'file_path' must be provided",
+            "source_type": None,
+            "source": None,
+            "content": None,
+            "metadata": None
+        }
+    
+    # Determine source type and validate
+    source_type = "url" if url else "file"
+    source = url if url else file_path
+    
+    # Additional validation for file paths
+    if file_path:
+        path = Path(file_path)
+        if not path.exists():
+            return {
+                "success": False,
+                "error": f"File not found: {file_path}",
+                "source_type": source_type,
+                "source": source,
+                "content": None,
+                "metadata": None
+            }
+        
+        # Security check - ensure no directory traversal
+        try:
+            # Resolve to absolute path and ensure it's not trying to access sensitive areas
+            path.resolve()
+            # You might want to add additional checks here based on your security requirements
+        except Exception as e:
+            return {
+                "success": False,
+                "error": f"Invalid file path: {str(e)}",
+                "source_type": source_type,
+                "source": source,
+                "content": None,
+                "metadata": None
+            }
+    
+    # Build extraction request
+    extraction_request = {}
+    if url:
+        extraction_request["url"] = url
+    else:
+        extraction_request["file_path"] = str(Path(file_path).resolve())
+    
+    # Track start time
+    start_time = datetime.utcnow()
+    
+    try:
+        # Use Content Core's extract_content with auto engine
+        logger.info(f"Extracting content from {source_type}: {source}")
+        
+        # Suppress stdout to prevent MoviePy and other libraries from interfering with MCP protocol
+        with suppress_stdout():
+            result = await cc.extract_content(extraction_request)
+        
+        # Calculate extraction time
+        extraction_time = (datetime.utcnow() - start_time).total_seconds()
+        
+        # Build response - result is a ProcessSourceOutput object
+        response = {
+            "success": True,
+            "error": None,
+            "source_type": source_type,
+            "source": source,
+            "content": result.content or "",
+            "metadata": {
+                "extraction_time_seconds": extraction_time,
+                "extraction_timestamp": start_time.isoformat() + "Z",
+                "content_length": len(result.content or ""),
+                "identified_type": result.identified_type or "unknown",
+                "identified_provider": result.identified_provider or "",
+            }
+        }
+        
+        # Add metadata from the result
+        if result.metadata:
+            response["metadata"].update(result.metadata)
+        
+        # Add specific metadata based on source type
+        if source_type == "url":
+            if result.title:
+                response["metadata"]["title"] = result.title
+            if result.url:
+                response["metadata"]["final_url"] = result.url
+        elif source_type == "file":
+            if result.title:
+                response["metadata"]["title"] = result.title
+            if result.file_path:
+                response["metadata"]["file_path"] = result.file_path
+            response["metadata"]["file_size"] = Path(file_path).stat().st_size
+            response["metadata"]["file_extension"] = Path(file_path).suffix
+        
+        logger.info(f"Successfully extracted content from {source_type}: {source}")
+        return response
+        
+    except Exception as e:
+        logger.error(f"Error extracting content from {source_type} {source}: {str(e)}")
+        return {
+            "success": False,
+            "error": str(e),
+            "source_type": source_type,
+            "source": source,
+            "content": None,
+            "metadata": {
+                "extraction_timestamp": start_time.isoformat() + "Z",
+                "error_type": type(e).__name__
+            }
+        }
+
+
+@mcp.tool
+async def extract_content(
+    url: Optional[str] = None,
+    file_path: Optional[str] = None
+) -> Dict[str, Any]:
+    """
+    Extract content from a URL or file using Content Core's auto engine.
+    
+    Args:
+        url: Optional URL to extract content from
+        file_path: Optional file path to extract content from
+        
+    Returns:
+        JSON object containing extracted content and metadata
+        
+    Raises:
+        ValueError: If neither or both url and file_path are provided
+    """
+    return await _extract_content_impl(url=url, file_path=file_path)
+
+
+def main():
+    """Entry point for the MCP server."""
+    # Additional MoviePy configuration to suppress all output
+    try:
+        import moviepy.config as mp_config
+        mp_config.check_and_download_cmd("ffmpeg")  # Pre-download to avoid logs later
+    except Exception:
+        pass  # Ignore if MoviePy isn't available or configured
+    
+    logger.info("Starting Content Core MCP Server")
+    
+    # Run with STDIO transport for MCP compatibility
+    mcp.run()
+
+
+if __name__ == "__main__":
+    main()

content_core/models.py

@@ -1,5 +1,4 @@
 from esperanto import AIFactory
-from esperanto.providers.stt import SpeechToTextModel
 from .config import CONFIG
 
 class ModelFactory:

{content_core-1.0.4.dist-info → content_core-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 1.0.4
+Version: 1.1.0
 Summary: Extract what matters from any media source
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
@@ -31,6 +31,8 @@ Requires-Dist: pytubefix>=9.1.1
 Requires-Dist: readability-lxml>=0.8.4.1
 Requires-Dist: validators>=0.34.0
 Requires-Dist: youtube-transcript-api>=1.0.3
+Provides-Extra: mcp
+Requires-Dist: fastmcp>=0.5.0; extra == 'mcp'
 Description-Content-Type: text/markdown
 
 # Content Core
@@ -57,6 +59,7 @@ The primary goal of Content Core is to simplify the process of ingesting content
     * For files: Tries Docling extraction first (for robust document parsing), then falls back to simple extraction if needed.
     * You can override this by specifying an engine, but `'auto'` is recommended for most users.
 *   **Content Cleaning (Optional):** Likely integrates with LLMs (via `prompter.py` and Jinja templates) to refine and clean the extracted content.
+*   **MCP Server:** Includes a Model Context Protocol (MCP) server for seamless integration with Claude Desktop and other MCP-compatible applications.
 *   **Asynchronous:** Built with `asyncio` for efficient I/O operations.
 
 ## Getting Started
@@ -66,8 +69,11 @@ The primary goal of Content Core is to simplify the process of ingesting content
 Install Content Core using `pip`:
 
 ```bash
-# Install the package (without Docling)
+# Install the package
 pip install content-core
+
+# Install with MCP server support
+pip install content-core[mcp]
 ```
 
 Alternatively, if you’re developing locally:
@@ -194,6 +200,38 @@ summary = await cc.summarize_content("long article text", context="explain to a
 
 For more information on how to use the Content Core library, including details on AI model configuration and customization, refer to our [Usage Documentation](docs/usage.md).
 
+## MCP Server Integration
+
+Content Core includes a Model Context Protocol (MCP) server that enables seamless integration with Claude Desktop and other MCP-compatible applications. The MCP server exposes Content Core's powerful extraction capabilities through a standardized protocol.
+
+### Quick Setup with Claude Desktop
+
+```bash
+# Install with MCP support
+pip install content-core[mcp]
+
+# Or use directly with uvx (no installation required)
+uvx --from "content-core[mcp]" content-core-mcp
+```
+
+Add to your `claude_desktop_config.json`:
+```json
+{
+  "mcpServers": {
+    "content-core": {
+      "command": "uvx",
+      "args": [
+        "--from",
+        "content-core[mcp]",
+        "content-core-mcp"
+      ]
+    }
+  }
+}
+```
+
+For detailed setup instructions, configuration options, and usage examples, see our [MCP Documentation](docs/mcp.md).
+
 ## Using with Langchain
 
 For users integrating with the [Langchain](https://python.langchain.com/) framework, `content-core` exposes a set of compatible tools. These tools, located in the `src/content_core/tools` directory, allow you to leverage `content-core` extraction, cleaning, and summarization capabilities directly within your Langchain agents and chains.

{content_core-1.0.4.dist-info → content_core-1.1.0.dist-info}/RECORD

@@ -1,8 +1,8 @@
 content_core/__init__.py,sha256=t4xFo9f3uB2FD1tdR-7ruhMW9_ciJawQReK6iFXWfR0,6531
 content_core/cc_config.yaml,sha256=gGSPM-oO6GIHyCfDCH-cN72BgPJiRmZMgwPrrLhUmfU,851
-content_core/config.py,sha256=vbRgJy8lOTZABeY7GZc7MglNYwBQYpUNzu76kprv_c0,1854
+content_core/config.py,sha256=vyx0fioR6r0mcZfVdwAFDhFrRNoG0ZNG8RNxIDnhNlo,1802
 content_core/logging.py,sha256=oeRdWKknEolptopxF1IvnEGEc0ZUw45QXYUEZ71GcdY,438
-content_core/models.py,sha256=FBV_tV6cmI0F82WfcA6xHag-YMsxI1dIbDGWG-3Eq_Y,935
+content_core/models.py,sha256=Kt6tWdAX87eQ2tL6eTwcHU7_NIRnN4exP4RzV2WrMig,881
 content_core/models_config.yaml,sha256=Yr-GS94ffxnkaWojUfpErUMM7m_MShsYjR6QuDjMzwo,444
 content_core/py.typed,sha256=pLuU3XTTeVpXo4UomOjcvAIQqOrzIotlWlJ3KFo2lxQ,154
 content_core/templated_message.py,sha256=KbI2rcvgGM5oRIcsG68zAZfgNsC97fR16D61683ZSnY,1617
@@ -19,6 +19,8 @@ content_core/content/extraction/graph.py,sha256=Nn2iaQc6YJ4Qt8WKTolwUQUNNqUlwpV8
 content_core/content/identification/__init__.py,sha256=x4n8JIjDwmPvAopEEEcmZjlozg-zGbMq_s9VYdBjzYU,169
 content_core/content/summary/__init__.py,sha256=ReKCZWKfDtqlInKeh87Y1DEfiNzVWabGybEz3hS2FrI,114
 content_core/content/summary/core.py,sha256=kEabpETljzUb-yf0NcVWTOuCtayESo74gGBVDX7YTFs,550
+content_core/mcp/__init__.py,sha256=KNZYH4F9AoW1Orw1BtO3n92Cn-127hI7iF9gnGadueU,95
+content_core/mcp/server.py,sha256=m2A63Qle3nJ_Lw46uWkwVvYERtEw84hd7NHAn1rwdAQ,6968
 content_core/notebooks/run.ipynb,sha256=WPBNcQUNXR5MldNMghVcU4vE4ibrVmlANa80baQn8TA,371078
 content_core/processors/audio.py,sha256=Mie20g_2Akhw6BHBVo3sHMpDRYUkqBI72lEDakscx3s,5729
 content_core/processors/docling.py,sha256=dkXehsQdfyWXfrK1K_6Pye50ABM7DxMk6TMguabM9Pc,2151
@@ -32,8 +34,8 @@ content_core/tools/__init__.py,sha256=DuJmd7fE-NpDvLP8IW1XY5MUkAQcdks52rn2jk4N8j
 content_core/tools/cleanup.py,sha256=5IdKedsFyRQMdYzgFSKtsfyxJldbroXQXHesHICNENI,523
 content_core/tools/extract.py,sha256=-r2_jsuMMXyXxGVqWhh1ilNPo_UMYAbw3Pkp1FzPy5g,577
 content_core/tools/summarize.py,sha256=DPfeglLWB08q8SvHrsKpOKZ35XjduUDs2J02ISwjdj0,596
-content_core-1.0.4.dist-info/METADATA,sha256=SdXexgOV0tc4ArCYWjxrZog4esHJxW0zh8pdnZFqLi8,11908
-content_core-1.0.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-content_core-1.0.4.dist-info/entry_points.txt,sha256=9fGQUk6bxBVXj9PRwfWVPn54ClSEJV7J-KBLXtjOhQw,99
-content_core-1.0.4.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
-content_core-1.0.4.dist-info/RECORD,,
+content_core-1.1.0.dist-info/METADATA,sha256=9-ppXQ7o-s8BCb2lH5xBiaiYBHmOFmXFrWntHuo9G_o,13017
+content_core-1.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+content_core-1.1.0.dist-info/entry_points.txt,sha256=ifbBxw37b7gAxZXoduS15KtqHuMHuU58STRkEmgM2zA,147
+content_core-1.1.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
+content_core-1.1.0.dist-info/RECORD,,

{content_core-1.0.4.dist-info → content_core-1.1.0.dist-info}/entry_points.txt

@@ -1,4 +1,5 @@
 [console_scripts]
 cclean = content_core:cclean
 ccore = content_core:ccore
+content-core-mcp = content_core.mcp.server:main
 csum = content_core:csum