Search & RAG Stack
Build retrieval-augmented generation pipelines with vector search, web crawling, knowledge graphs, and persistent memory.
Token Budget
This stack is lightweight. Plenty of room for your prompts and code context.
Config
Paste in ~/.claude.json
{
"mcpServers": {
"weaviate-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-weaviate"
],
"env": {
"WEAVIATE_URL": "YOUR_WEAVIATE_URL",
"WEAVIATE_API_KEY": "YOUR_WEAVIATE_API_KEY"
}
},
"pinecone-mcp": {
"command": "npx",
"args": [
"-y",
"@pinecone-database/mcp"
],
"env": {
"PINECONE_API_KEY": "YOUR_PINECONE_API_KEY"
}
},
"firecrawl-mcp": {
"command": "npx",
"args": [
"-y",
"firecrawl-mcp"
],
"env": {
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY"
}
},
"memory-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
},
"exa-mcp": {
"command": "npx",
"args": [
"-y",
"exa-mcp-server"
],
"env": {
"EXA_API_KEY": "YOUR_EXA_API_KEY"
}
},
"context7-mcp": {
"command": "npx",
"args": [
"-y",
"@upstash/context7-mcp"
]
}
}
}Included Servers
Pinecone MCP
Pinecone
Search Pinecone documentation, manage vector indexes, upsert data, query for relevant information, and rerank results from your AI editor.
Store and query high-dimensional vector embeddings at scale for fast, accurate semantic search across your knowledge base.
Weaviate MCP
Weaviate
Connect to Weaviate vector database collections for semantic search, knowledge base operations, and chat memory storage from your AI editor.
Run hybrid vector and keyword search with built-in vectorization modules — great for multi-modal RAG pipelines.
Exa Search MCP
Exa
AI-powered web search and crawling with Exa. Get semantically relevant results, extract content, and find similar pages.
Perform AI-native web search that understands semantic meaning, retrieving the most relevant sources for your RAG context window.
Context7 MCP
Upstash
Pull up-to-date documentation and code examples for any library directly into your prompt context using the Context7 API.
Pull current library and framework documentation into your retrieval pipeline so generated answers reflect the latest APIs.
Firecrawl MCP
Mendable
Scrape and crawl websites, extract structured data, and perform batch web scraping with LLM-powered content analysis.
Crawl and extract clean content from any website to build and refresh your RAG knowledge base automatically.
Memory MCP
Anthropic
Enable persistent memory for Claude through a knowledge graph. Store and retrieve entities, relations, and observations across sessions.
Persist conversation context, retrieved facts, and user preferences across sessions for continuity in multi-turn RAG applications.
Recommended Skills
Skills that pair with the servers in this stack. Learn more
For Firecrawl MCP
Web scraping and content extraction workflows using Firecrawl. Includes crawl configuration and data pipeline patterns.
npx skillsadd firecrawl/cli/firecrawl