Vector & AI Search Stack for Claude Code
Configuration
{
"mcpServers": {
"pinecone-mcp": {
"command": "npx",
"args": [
"-y",
"@pinecone-database/mcp"
],
"env": {
"PINECONE_API_KEY": "YOUR_PINECONE_API_KEY"
}
},
"weaviate-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-server-weaviate"
],
"env": {
"WEAVIATE_URL": "YOUR_WEAVIATE_URL",
"WEAVIATE_API_KEY": "YOUR_WEAVIATE_API_KEY"
}
},
"exa-mcp": {
"command": "npx",
"args": [
"-y",
"exa-mcp-server"
],
"env": {
"EXA_API_KEY": "YOUR_EXA_API_KEY"
}
},
"memory-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
},
"sequential-thinking-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-sequential-thinking"
]
},
"context7-mcp": {
"command": "npx",
"args": [
"-y",
"@upstash/context7-mcp"
]
}
}
}CLI Commands
Alternatively, add each server via the Claude Code CLI:
claude mcp add pinecone-mcp -e PINECONE_API_KEY=YOUR_PINECONE_API_KEY -- npx -y @pinecone-database/mcp
claude mcp add weaviate-mcp -e WEAVIATE_URL=YOUR_WEAVIATE_URL -e WEAVIATE_API_KEY=YOUR_WEAVIATE_API_KEY -- npx -y mcp-server-weaviate
claude mcp add exa-mcp -e EXA_API_KEY=YOUR_EXA_API_KEY -- npx -y exa-mcp-server
claude mcp add memory-mcp -- npx -y @modelcontextprotocol/server-memory
claude mcp add sequential-thinking-mcp -- npx -y @modelcontextprotocol/server-sequential-thinking
claude mcp add context7-mcp -- npx -y @upstash/context7-mcpWhere to save
Paste the config above into:
~/.claude.jsonEnvironment Variables
Replace the YOUR_ placeholders with your actual values.
PINECONE_API_KEYrequiredPinecone API key for authentication
Used by: Pinecone MCP
WEAVIATE_URLrequiredWeaviate instance URL
Used by: Weaviate MCP
WEAVIATE_API_KEYWeaviate API key for authentication
Used by: Weaviate MCP
EXA_API_KEYrequiredExa API key
Used by: Exa Search MCP
What’s in this stack
Search Pinecone documentation, manage vector indexes, upsert data, query for relevant information, and rerank results from your AI editor.
Index and query billions of vector embeddings with metadata filtering for production-scale semantic search applications.
Connect to Weaviate vector database collections for semantic search, knowledge base operations, and chat memory storage from your AI editor.
Combine vector similarity with keyword search and classification — a versatile engine for hybrid AI search architectures.
AI-powered web search and crawling with Exa. Get semantically relevant results, extract content, and find similar pages.
Search the web using natural language queries that understand intent, returning semantically relevant results instead of keyword matches.
Enable persistent memory for Claude through a knowledge graph. Store and retrieve entities, relations, and observations across sessions.
Store and recall search context, user preferences, and session history to personalize results and maintain continuity.
Enable structured, step-by-step reasoning for complex problem solving. Helps AI break down problems into logical sequences.
Break complex search queries into structured reasoning steps so your AI processes multi-faceted questions methodically.
Pull up-to-date documentation and code examples for any library directly into your prompt context using the Context7 API.
Retrieve current documentation for vector database SDKs and search libraries to ensure your implementation uses the latest APIs.