---
name: "Give MCP agents structured graph memory with RushDB"
slug: "give-mcp-agents-structured-graph-memory-with-rushdb"
description: "Connect RushDB's MCP server so agents can store, search, update, and traverse persistent structured memory without hand-building a separate vector and graph stack."
github_stars: 308
verification: "security_reviewed"
source: "https://github.com/rush-db/rushdb"
author: "RushDB"
publisher_type: "organization"
category: "Integrations & Connectors"
framework: "MCP"
tool_ecosystem:
  github_repo: "rush-db/rushdb"
  github_stars: 308
  npm_package: "@rushdb/mcp-server"
  npm_weekly_downloads: 1903
---

# Give MCP agents structured graph memory with RushDB

Connect RushDB's MCP server so agents can store, search, update, and traverse persistent structured memory without hand-building a separate vector and graph stack.

## Prerequisites

RushDB account or self-hosted RushDB API, RushDB API key, Node.js/npx, and an MCP-compatible client such as ChatGPT, Claude.ai, Claude Desktop, Cursor, Windsurf, VS Code, or Gemini CLI

## Installation

Use the upstream install or setup path that matches your environment:
- npm install @rushdb/javascript-sdk
- pip install rushdb
- git clone https://github.com/rush-db/rushdb.git
- pnpm install

Requirements and caveats from upstream:
- **Self-host** — Docker + your own Neo4j instance. [Jump to Self-hosting →](#self-hosting)
- python
- | Python SDK | https://docs.rushdb.com/python-sdk/introduction |

Basic usage or getting-started notes:
- Two paths depending on your setup:
- **Cloud** — Managed, free tier, running in 30 seconds. [Get API key →](https://app.rushdb.com)
- typescript

- Source: https://github.com/rush-db/rushdb
- Extracted from upstream docs: https://raw.githubusercontent.com/rush-db/rushdb/HEAD/README.md

## Documentation

- https://github.com/rush-db/rushdb/tree/main/packages/mcp-server

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/give-mcp-agents-structured-graph-memory-with-rushdb/)