Rich Link Previews with One API Call Extract Open Graph, Twitter Cards, favicons, JSON-LD, and structured metadata from any URL. Power beautiful link previews in your app in minutes, not days.
Scored across 3 tools
The tools have overlapping purposes that could cause confusion. 'batch_extract_metadata' and 'extract_metadata' both extract metadata from URLs, with the batch version handling multiple URLs. 'validate_metadata' is more distinct but still operates on the same domain. Descriptions help clarify the differences, but the overlap between the first two tools is notable.
All tool names follow a consistent verb_noun pattern using snake_case. 'batch_extract_metadata', 'extract_metadata', and 'validate_metadata' are uniformly structured, making them predictable and easy to understand at a glance.
With only 3 tools, the server feels thin for a metadata extraction domain. While the tools cover extraction and validation, the scope might benefit from additional operations like updating or managing metadata, making the count borderline for comprehensive coverage.
The tool set covers core metadata operations: extraction (single and batch) and validation. However, there are minor gaps, such as no tools for updating metadata or handling metadata storage, which agents might need to work around for full lifecycle management.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
validate_metadatabatch_extract_metadata1 field changedInput schema / properties / fields / descriptionPrevious value: -"Comma-separated fields to return (e.g. \"title,body,summary,redirectChain\"). Include \"body\" for clean extracted page text."New value: +"Comma-separated fields to return (e.g. \"title,body,summary,statusCode,contentType\"). Include \"body\" for clean extracted page text."extract_metadata1 field changedInput schema / properties / fields / descriptionPrevious value: -"Comma-separated fields to return (e.g. \"title,body,summary,redirectChain\"). Include \"body\" for clean extracted page text. Available: url,title,description,image,favicon,siteName,type,locale,language,author,publishedDate,modifiedDate,keywords,themeColor,canonical,wordCount,summary,body,redirectChain,twitter,openGraph,jsonLd,responseTime"New value: +"Comma-separated fields to return (e.g. \"title,body,summary,statusCode,contentType\"). Include \"body\" for clean extracted page text. Available: url,statusCode,contentType,title,description,image,favicon,siteName,type,locale,language,author,publishedDate,modifiedDate,keywords,themeColor,canonical,wordCount,summary,body,redirectChain,twitter,openGraph,jsonLd,responseTime"batch_extract_metadata2 fields changedInput schema / properties / fields / descriptionPrevious value: -"Comma-separated fields to return (e.g. \"title,body,summary\"). Include \"body\" for clean extracted page text."New value: +"Comma-separated fields to return (e.g. \"title,body,summary,redirectChain\"). Include \"body\" for clean extracted page text."Input schema / properties / timeoutAdded value: +{
+ "description": "Request timeout in milliseconds (default 10000, max 30000). Increase for slow-responding targets.",
+ "type": "number"
+}extract_metadata2 fields changedInput schema / properties / fields / descriptionPrevious value: -"Comma-separated fields to return (e.g. \"title,body,summary\"). Include \"body\" for clean extracted page text. Available: url,title,description,image,favicon,siteName,type,locale,language,author,publishedDate,modifiedDate,keywords,themeColor,canonical,wordCount,summary,body,twitter,openGraph,jsonLd,responseTime"New value: +"Comma-separated fields to return (e.g. \"title,body,summary,redirectChain\"). Include \"body\" for clean extracted page text. Available: url,title,description,image,favicon,siteName,type,locale,language,author,publishedDate,modifiedDate,keywords,themeColor,canonical,wordCount,summary,body,redirectChain,twitter,openGraph,jsonLd,responseTime"Input schema / properties / timeoutAdded value: +{
+ "description": "Request timeout in milliseconds (default 10000, max 30000). Increase for slow-responding targets.",
+ "type": "number"
+}batch_extract_metadata2 fields changedInput schema / properties / fieldsAdded value: +{
+ "description": "Comma-separated fields to return (e.g. \"title,body,summary\"). Include \"body\" for clean extracted page text.",
+ "type": "string"
+}Input schema / properties / summary_lengthAdded value: +{
+ "description": "Max summary length in characters (default 300, max 2000)",
+ "type": "number"
+}extract_metadata2 fields changedInput schema / properties / fieldsAdded value: +{
+ "description": "Comma-separated fields to return (e.g. \"title,body,summary\"). Include \"body\" for clean extracted page text. Available: url,title,description,image,favicon,siteName,type,locale,language,author,publishedDate,modifiedDate,keywords,themeColor,canonical,wordCount,summary,body,twitter,openGraph,jsonLd,responseTime",
+ "type": "string"
+}Input schema / properties / summary_lengthAdded value: +{
+ "description": "Max summary length in characters (default 300, max 2000)",
+ "type": "number"
+}batch_extract_metadataextract_metadata
Add one secure layer between your agents and this server.
