ddgs-mcp-server 0.4.1__py3-none-any.whl → 0.5.0__py3-none-any.whl

ddgs_mcp_server/server.py

@@ -1,7 +1,11 @@
 
 import json
 import logging
-from typing import Optional, Literal
+import asyncio
+from typing import Optional
+
+import httpx
+import trafilatura
 from mcp.server import Server
 import mcp.types as types
 from ddgs import DDGS
@@ -13,12 +17,94 @@ logger = logging.getLogger("ddgs-mcp")
 # MCP Server
 server = Server("ddgs-mcp-server")
 
+# --- Content Extraction Utilities ---
+
+async def fetch_page_content(
+    url: str,
+    timeout: int = 10,
+    max_length: int = 50000
+) -> Optional[str]:
+    """
+    Fetch and extract main text content from a URL using trafilatura.
+
+    Args:
+        url: The URL to fetch content from
+        timeout: Request timeout in seconds
+        max_length: Maximum characters to return
+
+    Returns:
+        Extracted text content or None on failure
+    """
+    try:
+        async with httpx.AsyncClient(
+            timeout=timeout,
+            follow_redirects=True,
+            verify=True
+        ) as client:
+            response = await client.get(url, headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+                "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+                "Accept-Language": "en-US,en;q=0.5",
+            })
+            if response.status_code == 200:
+                downloaded = response.text
+                # Extract main content using trafilatura
+                extracted = trafilatura.extract(
+                    downloaded,
+                    include_links=False,
+                    include_images=False,
+                    include_comments=False,
+                    favor_precision=True
+                )
+                if extracted:
+                    return extracted[:max_length]
+    except httpx.TimeoutException:
+        logger.warning(f"Timeout fetching {url}")
+    except httpx.HTTPError as e:
+        logger.warning(f"HTTP error fetching {url}: {e}")
+    except Exception as e:
+        logger.warning(f"Failed to fetch {url}: {e}")
+    return None
+
+
+async def enrich_results_with_content(
+    results: list,
+    max_concurrent: int = 5,
+    max_length: int = 50000
+) -> list:
+    """
+    Fetch full content for all search results concurrently.
+
+    Args:
+        results: List of search result dictionaries
+        max_concurrent: Maximum concurrent requests
+        max_length: Maximum content length per page
+
+    Returns:
+        Results list with 'full_content' field added
+    """
+    semaphore = asyncio.Semaphore(max_concurrent)
+
+    async def fetch_with_semaphore(result: dict) -> dict:
+        async with semaphore:
+            url = result.get("href")
+            if url:
+                content = await fetch_page_content(url, max_length=max_length)
+                result["full_content"] = content if content else "[Content extraction failed or blocked]"
+            return result
+
+    tasks = [fetch_with_semaphore(r.copy()) for r in results]
+    return await asyncio.gather(*tasks)
+
+
+# --- MCP Tool Definitions ---
+
 @server.list_tools()
 async def list_tools() -> list[types.Tool]:
     return [
         types.Tool(
             name="search_text",
-            description="Perform a metasearch using various backends (DuckDuckGo, Google, Bing, etc.). Use this to find APIs, libraries, developer tools, and general information.",
+            description="Perform a metasearch using various backends (DuckDuckGo, Google, Bing, etc.). Use this to find APIs, libraries, developer tools, and general information. Optionally fetch full page content for complete context.",
             inputSchema={
                 "type": "object",
                 "properties": {
@@ -32,7 +118,17 @@ async def list_tools() -> list[types.Tool]:
                     "region": {"type": "string", "default": "us-en", "description": "e.g., us-en, uk-en"},
                     "safesearch": {"type": "string", "enum": ["on", "moderate", "off"], "default": "moderate"},
                     "timelimit": {"type": "string", "enum": ["d", "w", "m", "y"], "default": None},
-                    "max_results": {"type": "integer", "default": 10}
+                    "max_results": {"type": "integer", "default": 10},
+                    "fetch_full_content": {
+                        "type": "boolean",
+                        "default": False,
+                        "description": "If true, fetches and returns the full text content of each result page. This provides complete context but adds latency."
+                    },
+                    "max_content_length": {
+                        "type": "integer",
+                        "default": 50000,
+                        "description": "Maximum characters of content to fetch per page (only used if fetch_full_content is true)."
+                    }
                 },
                 "required": ["query"]
             }
@@ -54,6 +150,7 @@ async def list_tools() -> list[types.Tool]:
         )
     ]
 
+
 @server.call_tool()
 async def call_tool(name: str, arguments: dict) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
     logger.info(f"Calling tool: {name} with args: {arguments}")
@@ -68,6 +165,10 @@ async def call_tool(name: str, arguments: dict) -> list[types.TextContent | type
     timelimit = arguments.get("timelimit")
     max_results = arguments.get("max_results", 10)
 
+    # New parameters for full content extraction
+    fetch_full_content = arguments.get("fetch_full_content", False)
+    max_content_length = arguments.get("max_content_length", 50000)
+
     try:
         with DDGS() as ddgs:
             results = []
@@ -80,6 +181,19 @@ async def call_tool(name: str, arguments: dict) -> list[types.TextContent | type
                     max_results=max_results,
                     backend=backend
                 )
+
+                # Convert generator to list for manipulation
+                results = list(results) if results else []
+
+                # Enrich with full content if requested
+                if fetch_full_content and results:
+                    logger.info(f"Fetching full content for {len(results)} results...")
+                    results = await enrich_results_with_content(
+                        results,
+                        max_length=max_content_length
+                    )
+                    logger.info("Full content extraction complete")
+
             elif name == "search_news":
                 results = ddgs.news(
                     query=query,
@@ -88,6 +202,7 @@ async def call_tool(name: str, arguments: dict) -> list[types.TextContent | type
                     timelimit=timelimit,
                     max_results=max_results
                 )
+                results = list(results) if results else []
 
             return [types.TextContent(type="text", text=json.dumps(results, indent=2))]
 

{ddgs_mcp_server-0.4.1.dist-info → ddgs_mcp_server-0.5.0.dist-info}/METADATA

@@ -1,11 +1,13 @@
 Metadata-Version: 2.4
 Name: ddgs-mcp-server
-Version: 0.4.1
-Summary: DuckDuckGo Search MCP Server
+Version: 0.5.0
+Summary: DuckDuckGo Search MCP Server with full page content extraction
 License-File: LICENSE
 Requires-Python: >=3.10
 Requires-Dist: ddgs>=9.10.0
+Requires-Dist: httpx>=0.27.0
 Requires-Dist: mcp>=1.0.0
+Requires-Dist: trafilatura>=2.0.0
 Description-Content-Type: text/markdown
 
 # DDGS MCP Server
@@ -14,9 +16,54 @@ A Model Context Protocol (MCP) server that provides DuckDuckGo Search capabiliti
 
 ## Features
 
-- **search_text**: advanced metasearch using `bing`, `brave`, `duckduckgo`, `google`, `mojeek`, `yahoo`, `yandex`, `wikipedia`.
+- **search_text**: Advanced metasearch using `bing`, `brave`, `duckduckgo`, `google`, `mojeek`, `yahoo`, `yandex`, `wikipedia`.
+  - **Full Content Extraction**: Optionally fetch complete page content (not just snippets) for comprehensive context.
 - **search_news**: Find latest updates, releases, and tech news.
 
+## Full Content Extraction
+
+For coding agents that need complete context from search results, enable full page content fetching:
+
+### Usage
+
+```json
+{
+  "query": "python async programming tutorial",
+  "fetch_full_content": true,
+  "max_content_length": 50000,
+  "max_results": 5
+}
+```
+
+### Parameters
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `fetch_full_content` | boolean | `false` | Enable full page content extraction |
+| `max_content_length` | integer | `50000` | Maximum characters per page (when `fetch_full_content` is true) |
+
+### Response Structure
+
+When `fetch_full_content` is enabled, each result includes a `full_content` field:
+
+```json
+[
+  {
+    "title": "Python Async Programming Guide",
+    "href": "https://example.com/python-async",
+    "body": "Brief snippet from search results...",
+    "full_content": "Complete extracted article text with all paragraphs, code examples, and detailed explanations..."
+  }
+]
+```
+
+### Performance Notes
+
+- Content extraction adds ~1-3 seconds latency per page
+- Up to 5 pages are fetched concurrently to minimize total time
+- Failed fetches return `[Content extraction failed or blocked]` without breaking the search
+- Uses [Trafilatura](https://trafilatura.readthedocs.io/) for high-quality text extraction
+
 
 ## Installation & Usage
 

ddgs_mcp_server-0.5.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+ddgs_mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+ddgs_mcp_server/main.py,sha256=hqJl7UoGQoL9a-2hX24srZYFGdatheJfgkn5wz5Od70,492
+ddgs_mcp_server/server.py,sha256=jFfmXEFCoSQh3W0-DmlVAcZCcFu5GEKWRLo0cdZsSU8,8249
+ddgs_mcp_server-0.5.0.dist-info/METADATA,sha256=ZHDmduec9GXJ-ufpGuG1NhAYrnIS0GYGwkV8AMvDiNQ,3757
+ddgs_mcp_server-0.5.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+ddgs_mcp_server-0.5.0.dist-info/entry_points.txt,sha256=8YvtzhkNDMvAy2CdIx8VppBFjiBSJ56JtLX-v8SUHGc,62
+ddgs_mcp_server-0.5.0.dist-info/licenses/LICENSE,sha256=vLPKcNOa4dGBRPq4I_mIBKyVSbIlzrOdinbwXFeKb88,1091
+ddgs_mcp_server-0.5.0.dist-info/RECORD,,

ddgs_mcp_server-0.4.1.dist-info/RECORD

@@ -1,8 +0,0 @@
-ddgs_mcp_server/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ddgs_mcp_server/main.py,sha256=hqJl7UoGQoL9a-2hX24srZYFGdatheJfgkn5wz5Od70,492
-ddgs_mcp_server/server.py,sha256=IEsDiPsw2ciIVnmoOBYnOuVd_fCXmOXfNapQTBpO9wc,3919
-ddgs_mcp_server-0.4.1.dist-info/METADATA,sha256=bylRyAQpkCOFQilQt-rMLuP1j4eOxLMZjQsZMyVqyyE,2227
-ddgs_mcp_server-0.4.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-ddgs_mcp_server-0.4.1.dist-info/entry_points.txt,sha256=8YvtzhkNDMvAy2CdIx8VppBFjiBSJ56JtLX-v8SUHGc,62
-ddgs_mcp_server-0.4.1.dist-info/licenses/LICENSE,sha256=vLPKcNOa4dGBRPq4I_mIBKyVSbIlzrOdinbwXFeKb88,1091
-ddgs_mcp_server-0.4.1.dist-info/RECORD,,