search_media
Find images or videos using a privacy-focused search tool that aggregates results from multiple engines without tracking user data.
Instructions
Search for images or videos.
Use this when:
User wants to find images or photos
Looking for video content
"show me pictures of..." or "find videos about..."
Parameters: query* - What to find media_type - "images" or "videos" (default: images) engines - Optional: Specific engines max_results - Number of results (default: 10, max: 50)
Returns: Media URLs with thumbnails and sources
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Media search query | |
| media_type | No | Type of media | images |
| engines | No | Comma-separated engine list | |
| max_results | No | Maximum results |
Implementation Reference
- src/searxng_mcp/tools/search.py:129-172 (handler)The core handler function implementing the search_media tool logic. It queries the SearXNG API with the specified media category (images/videos), processes the results, and formats them into a markdown-style TextContent response.
def search_media( self, query: str, media_type: Literal["images", "videos"] = "images", engines: Optional[str] = None, max_results: int = 10 ) -> List[TextContent]: """Search for images or videos. Args: query: Search query media_type: "images" or "videos" engines: Comma-separated engine list max_results: Maximum results to return Returns: Formatted media search results """ results = self._search(query, category=media_type, engines=engines) if media_type == "images": output = f"🖼️ Image Results for: {query}\n\n" for i, result in enumerate(results.get("results", [])[:max_results], 1): output += f"{i}. **{result.get('title', 'No title')}**\n" output += f" URL: {result.get('img_src', 'N/A')}\n" output += f" Source: {result.get('url', 'N/A')}\n" if result.get('thumbnail_src'): output += f" Thumbnail: {result['thumbnail_src']}\n" output += "\n" else: # videos output = f"🎥 Video Results for: {query}\n\n" for i, result in enumerate(results.get("results", [])[:max_results], 1): output += f"{i}. **{result.get('title', 'No title')}**\n" output += f" {result.get('url', '')}\n" if result.get('content'): output += f" {result['content']}\n" if result.get('publishedDate'): output += f" Published: {result['publishedDate']}\n" output += "\n" if not results.get("results"): output += f"No {media_type} found.\n" return [TextContent(type="text", text=output)] - src/searxng_mcp/server.py:149-156 (registration)MCP tool registration for search_media using FastMCP decorator, including input schema via Annotated Fields. Delegates execution to the SearchTools instance.
@self.mcp.tool(description=SEARCH_MEDIA_DESC) def search_media( query: Annotated[str, Field(description="Media search query")], media_type: Annotated[Literal["images", "videos"], Field(description="Type of media")] = "images", engines: Annotated[Optional[str], Field(description="Comma-separated engine list")] = None, max_results: Annotated[int, Field(description="Maximum results", ge=1, le=50)] = 10 ): return self.search_tools.search_media(query, media_type, engines, max_results) - src/searxng_mcp/server.py:32-45 (schema)Tool description string providing usage guidelines, parameters, and return format for the search_media tool.
SEARCH_MEDIA_DESC = """Search for images or videos. Use this when: - User wants to find images or photos - Looking for video content - "show me pictures of..." or "find videos about..." Parameters: query* - What to find media_type - "images" or "videos" (default: images) engines - Optional: Specific engines max_results - Number of results (default: 10, max: 50) Returns: Media URLs with thumbnails and sources"""