AI-powered content extraction
## Jina AI MCP Server: Neural Search and Reading The **Jina AI MCP Server** integrates Jina AI services directly into Google Antigravity, enabling AI assistants to perform neural search, web reading, and content embedding programmatically. This integration brings advanced AI-powered content processing to your development workflow. ### Why Jina AI MCP? - **Reader API**: Extract clean, readable content from any URL - **Neural Search**: Semantic search across documents and data - **Embeddings**: Generate embeddings for text and multi-modal content - **Reranking**: Improve search relevance with neural reranking - **Segmentation**: Intelligent document chunking and segmentation ### Key Features #### 1. Web Reading ```python from anthropic import Anthropic client = Anthropic() response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Read this article URL and extract the clean content for analysis" }], tools=[{ "name": "jina_reader", "description": "Read web content" }] ) ``` #### 2. Embedding Generation ```python # Generate embeddings response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Generate embeddings for these documents for semantic search" }], tools=[{"name": "jina_embed", "description": "Generate embeddings"}] ) ``` #### 3. Neural Search ```python # Semantic search response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Search our document collection for content about authentication patterns" }], tools=[{"name": "jina_search", "description": "Neural search"}] ) ``` #### 4. Result Reranking ```python # Rerank search results response = client.messages.create( model="claude-sonnet-4-20250514", max_tokens=1024, messages=[{ "role": "user", "content": "Rerank these search results for better relevance to the query" }], tools=[{"name": "jina_rerank", "description": "Rerank results"}] ) ``` ### Configuration ```json { "mcpServers": { "jina-ai": { "command": "npx", "args": ["-y", "@anthropic/mcp-jina"], "env": { "JINA_API_KEY": "your-jina-api-key" } } } } ``` ### Use Cases **Content Processing**: Extract and process web content for analysis and storage. **Semantic Search**: Build search systems that understand meaning, not just keywords. **RAG Applications**: Generate embeddings for retrieval-augmented generation. **Document Processing**: Segment and embed documents for intelligent retrieval. The Jina AI MCP Server brings advanced neural content processing directly into your development workflow, enabling AI-powered information retrieval.
{
"mcpServers": {
"jina-ai": {
"mcpServers": {
"jina": {
"url": "https://mcp.jina.ai/sse",
"type": "sse"
}
}
}
}
}