AINative ZeroDB MCP Server
Provides AI assistants with vector search and persistent memory capabilities using ZeroDB. Enables storing and retrieving context across sessions, semantic document search, and analytics through natural language interactions.
README
🚀 AINative ZeroDB MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with vector search and persistent memory capabilities using ZeroDB.
Features
- 🧠 Persistent Memory - Store and retrieve context across sessions
- 🔍 Vector Search - Semantic similarity search across documents
- 📊 Analytics - Query insights and usage patterns
- 🔐 Project Isolation - Separate data by project
- ⚡ High Performance - Optimized for real-time AI interactions
Quick Start
Installation
# Install globally
npm install -g ainative-zerodb-mcp-server
# Or use with npx
npx ainative-zerodb-mcp-server
Add to Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"zerodb": {
"command": "npx",
"args": ["-y", "ainative-zerodb-mcp-server"],
"env": {
"ZERODB_API_URL": "https://api.ainative.studio/api/v1",
"ZERODB_PROJECT_ID": "your-project-id",
"ZERODB_USERNAME": "your-username",
"ZERODB_PASSWORD": "your-password"
}
}
}
}
Add to Claude Code
# Add to current project
claude mcp add project zerodb npx -- -y ainative-zerodb-mcp-server
# Or add to .mcp.json
Available Tools
zerodb_store_memory
Store agent memory for persistent context across sessions.
{
"content": "User prefers dark mode themes",
"role": "assistant",
"session_id": "session-123",
"metadata": { "category": "preferences" }
}
zerodb_retrieve_memory
Retrieve stored memories and context.
{
"session_id": "session-123",
"limit": 10,
"role": "assistant"
}
zerodb_search
Semantic search across stored documents and memories.
{
"query": "user interface preferences",
"limit": 5,
"threshold": 0.7
}
zerodb_store_vector
Store embeddings for vector similarity search.
{
"content": "Technical documentation about APIs",
"vector": [0.1, 0.2, ...],
"metadata": { "type": "documentation" }
}
zerodb_analytics
Query analytics and insights.
{
"metric": "memory_usage",
"period": "7d"
}
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
ZERODB_API_URL |
ZeroDB API endpoint | https://api.ainative.studio/api/v1 |
ZERODB_PROJECT_ID |
Your project identifier | Required |
ZERODB_USERNAME |
Authentication username | Required |
ZERODB_PASSWORD |
Authentication password | Required |
ZERODB_API_TOKEN |
API token (if available) | Optional |
MCP_CONTEXT_WINDOW |
Context window size | 8192 |
MCP_RETENTION_DAYS |
Data retention period | 30 |
Usage Examples
With Claude Desktop
Once configured, you can use natural language:
- "Remember that the user prefers dark mode"
- "What do you know about my preferences?"
- "Search for information about API documentation"
- "Show me analytics for the last week"
Programmatic Usage
const { ZeroDBMCPServer } = require('ainative-zerodb-mcp-server');
const server = new ZeroDBMCPServer({
apiUrl: 'https://api.ainative.studio/api/v1',
projectId: 'my-project',
username: 'user@example.com',
password: 'secure-password'
});
await server.start();
Development
# Clone the repository
git clone https://github.com/AINative-Studio/ainative-zerodb-mcp-server.git
cd ainative-zerodb-mcp-server
# Install dependencies
npm install
# Run locally
npm start
# Run tests
npm test
Architecture
The ZeroDB MCP Server integrates with:
- ZeroDB API - Vector database backend
- MCP Protocol - Communication with AI assistants
- Token Management - Automatic token renewal
- Error Handling - Graceful fallbacks
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
MIT License - see LICENSE file for details
Support
- 📧 Email: support@ainative.studio
- 💬 Discord: Join our community
- 🐛 Issues: GitHub Issues
Related Projects
Made with ❤️ by AINative Studio
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.