Connect

Connect RushDB

Start with the path that matches how you work. Each option gets you to a working RushDB connection first, then points to the next useful workflow.

Goal	Fastest path	Time
Use RushDB from ChatGPT or Claude.ai	Hosted MCP connector	~1 min
Give Cursor, Claude Desktop, or VS Code RushDB tools	Local MCP server	~3 min
Teach an AI agent correct RushDB workflows	Install Agent Skills	~2 min
Add persistent memory to an agent	Bootstrap agent memory	~5 min
Build an application or data pipeline	Use an SDK or REST	~5 min

Need an API key for a local or application connection? Create one in the dashboard.

Hosted MCP Connector

For ChatGPT, Claude.ai, and other web-based MCP clients, add this URL as a connector:

https://mcp.rushdb.com/mcp

Verify:

Call getOntologyMarkdown and show me what labels exist in my RushDB project.

Set up a hosted MCP connector →

Local MCP Server

For Claude Desktop, Cursor, VS Code, and other local MCP clients, run the MCP server with your project API key:

{
  "mcpServers": {
    "rushdb": {
      "command": "npx",
      "args": ["-y", "@rushdb/mcp-server"],
      "env": {
        "RUSHDB_API_KEY": "your-api-key-here"
      }
    }
  }
}

Restart your client, then run the same ontology verification prompt.

Choose your local MCP client →

Install Agent Skills

Install RushDB Agent Skills so your assistant knows how to query, model data, and manage persistent memory:

npx skills add rush-db/rushdb --path packages/skills

Start a new agent session after installation so the skills are discovered.

Install and verify Agent Skills →

Bootstrap Agent Memory

After MCP and Skills are installed, give your agent the canonical machine-readable setup guide:

Fetch https://rushdb.com/agent-setup and follow the instructions exactly.

The agent discovers the live schema, creates a SESSION, imports existing preferences when available, and validates recall.

Bootstrap persistent memory →

Use an SDK or REST

For application code, use the TypeScript SDK, Python SDK, or JSON REST API. The first useful test is a nested import: RushDB creates the records and their relationships in one request.

curl -X POST https://api.rushdb.com/api/v1/records/import/json \
  -H "Authorization: Bearer $RUSHDB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "label": "PROJECT",
    "data": {
      "name": "RushDB adoption",
      "TASK": [
        {"title": "Connect RushDB", "status": "done"},
        {"title": "Query linked records", "status": "pending"}
      ]
    }
  }'

Connect with TypeScript, Python, or REST →

Choose What to Build

Use case	Guide
Persistent agent memory	Agent Memory Quickstart
Semantic search over your data	Semantic Search
Graph-enriched retrieval	GraphRAG Tutorial
Explore an unknown dataset safely	Discovery Queries
Design labels and relationships	Data Modeling

Hosted MCP Connector​

Local MCP Server​

Install Agent Skills​

Bootstrap Agent Memory​

Use an SDK or REST​