RushDB
Zero-config graph DB for builders, AI agents, and SaaS teams who move fast
README
RushDB MCP Server
A Model Context Protocol server providing access to RushDB's Labeled Meta Property Graph (LMPG) database.
Features
- Record Management: Create, read, update, and delete records
- Graph Operations: Attach and detach relationships between records
- Advanced Querying: Search across records using RushDB's flexible query language
- Label & Property Discovery: Browse labels and properties in your database
- Bulk Operations: Efficient bulk create and delete operations
- Data Export: Export records to CSV format
- LMPG Architecture: Work with RushDB's revolutionary property-first graph model
Quick Start
-
Install the package:
npm install -g @rushdb/mcp-server -
Get your RushDB API key from app.rushdb.com
-
Configure your MCP client (e.g., Claude Desktop):
{ "mcpServers": { "rushdb": { "command": "npx", "args": ["@rushdb/mcp-server"], "env": { "RUSHDB_API_KEY": "your-rushdb-api-key-here", "RUSHDB_API_URL": "https://api.rushdb.com/api/v1" } } } }Note:
RUSHDB_API_URLis optional and defaults tohttps://api.rushdb.com/api/v1. Override it for self-hosted or staging environments.
Available Tools
Database Discovery
FindLabels- List / filter record labels and their countsFindProperties- List / filter propertiesFindRelationships- Search for relationships
Record Operations
CreateRecord- Create a new recordUpdateRecord- Update an existing recordDeleteRecord- Delete a record by IDGetRecord- Retrieve a record by IDFindRecords- Search for records using query conditions
Relationship Management
AttachRelation- Create relationships between recordsDetachRelation- Remove relationships between recordsFindRelationships- Search for relationships
Bulk Operations
BulkCreateRecords- Create multiple records at onceBulkDeleteRecords- Delete multiple records matching a query
Data Export
ExportRecords- Export records to CSV format
Utilities
OpenBrowser- Open URLs in browserHelpAddToClient- Get setup instructionsGetQueryBuilderPrompt- Returns the RushDB Query Builder system prompt (fallback for clients without MCP Prompts support)
Built-in Query Builder Prompt (MCP Prompts)
This server exposes a system prompt via the MCP Prompts API to ensure discovery-first, schema-safe querying:
- Prompt name:
rushdb.queryBuilder - Purpose: guides the model to discover labels/properties first (FindLabels/FindProperties), then construct validated SearchQuery objects before calling find-related tools.
How clients should use it:
- Call
ListPromptsand look forrushdb.queryBuilder. - Call
GetPromptwith that name and set the returned system message for the model session that will use RushDB tools.
Most MCP clients can do this automatically at session start. If your client does not yet support Prompts, fetch this prompt once and inject it as the conversation’s system message before using RushDB tools.
Fallback tool for non-Prompts clients:
- Call
GetQueryBuilderPromptand set the returned text as your session’s system message.
Registry & Autodiscovery
- Manifest: a top-level
mcp.yamlis provided so MCP registries and clients can auto-discover this server. - Glama: see
packages/mcp-server/glama.jsonfor basic metadata. - When registering, use package
@rushdb/mcp-server, commandnpx, and ensureRUSHDB_API_KEYis set.
Environment Variables
RUSHDB_API_KEY- Your RushDB API key (required)RUSHDB_API_URL- RushDB API base URL (optional, defaults to https://api.rushdb.com/api/v1). Useful for self-hosted, on-prem, or staging deployments.
About RushDB's LMPG Architecture
RushDB uses a revolutionary Labeled Meta Property Graph (LMPG) architecture where:
- Properties are first-class citizens with their own nodes
- Records are connected through shared properties
- Relationships emerge automatically based on property overlap
- No rigid schemas - data structure evolves naturally
- Cross-domain insights through property traversal
This enables unprecedented flexibility in data modeling and querying.
Development
To build from source:
git clone <repository>
cd rushdb/packages/mcp-server
npm install
npm run build
License
Apache 2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。