Data Nexus MCP
Enables AI agents to interact with over 50 SQL and NoSQL databases through MCP tools for querying, schema inspection, and table management.
README
Data Nexus MCP
A modular, secure platform for connecting to SQL and NoSQL databases via REST API, MCP (Model Context Protocol), and a Vue.js Web UI.
Architecture
┌─────────────┐ ┌──────────────┐ ┌─────────────────┐
│ Web UI │────▶│ REST API │────▶│ core-db-command │
│ (Vue.js) │ │ (FastAPI) │ │ (Python lib) │
└─────────────┘ └──────┬───────┘ └────────┬────────┘
│ │
┌──────▼───────┐ │
│ MCP Server │───────────────┘
└──────┬───────┘
│
┌──────▼───────┐
│ MCP Client │──▶ AI Agents / LLMs
└──────────────┘
Modules
| Module | Package | Description |
|---|---|---|
| core-db-command | core_db_command/ |
Plugin-based Python library for all database drivers |
| rest-api-command | rest_api_command/ |
FastAPI REST layer with OAuth2/LDAP/basic auth |
| mcp-server | mcp_server/ |
MCP tools: query_database, get_schema, list_tables, describe_table, execute_sql |
| mcp-client | mcp_client/ |
MCP client bridge for agent integration |
| web-ui | web-ui/ |
Vue 3 + Pinia + Monaco Editor query studio |
| config | config/ |
YAML connection definitions with ${ENV} substitution |
Supported Database Types
The driver registry supports 50+ database types across 13 categories:
- Relational: PostgreSQL, MySQL, MSSQL, Oracle, CockroachDB, TiDB, YugabyteDB, TimescaleDB, pgvector
- Document: MongoDB, DocumentDB, Firestore, Couchbase (stub)
- Key-Value: Redis, DynamoDB, Memcached/etcd/RocksDB (stub)
- Wide-Column: Cassandra, ScyllaDB, Bigtable/HBase (stub)
- Graph: Neo4j, Neptune/JanusGraph/ArangoDB (stub)
- Time-Series: InfluxDB, ClickHouse, Prometheus/QuestDB (stub)
- Vector: Qdrant, Weaviate, Milvus, Pinecone
- Search: Elasticsearch, OpenSearch, Splunk/Solr (stub)
- Warehouse: BigQuery, Snowflake, Redshift/Databricks (stub)
- Multi-Model: Cosmos DB, OrientDB (stub)
- Embedded: SQLite, DuckDB, Realm/LMDB (stub)
- Ledger: QLDB/BigchainDB (stub)
- NewSQL: Spanner (stub)
Fully implemented drivers include PostgreSQL, MySQL, MSSQL, Oracle, MongoDB, Redis, SQLite, DuckDB, Elasticsearch, ClickHouse, Neo4j, InfluxDB, Cassandra, DynamoDB, BigQuery, Snowflake, Qdrant, Weaviate, Milvus, Pinecone, Cosmos DB, and Firestore. Stub drivers are registered and extensible.
Quick Start
Prerequisites
- Python 3.11+
- Node.js 20+ (for Web UI development)
- Docker & Docker Compose (optional)
1. Install Python dependencies
cp .env.example .env
pip install -e ".[dev]"
2. Configure connections
Edit config/connections.yaml and set secrets via environment variables:
connections:
- name: postgres_prod
type: postgresql
host: localhost
port: 5432
database: mydb
user: readonly_user
password: ${PG_PASSWORD}
3. Start the REST API
db-rest-api
# or: uvicorn rest_api_command.app:app --reload
API docs: http://localhost:8000/docs
4. Start the Web UI (development)
cd web-ui
cp .env.example .env
npm install
npm run dev
Open http://localhost:5173 — default credentials: admin / changeme
5. Run with Docker Compose
docker compose up -d
Services:
- REST API: http://localhost:8000
- Web UI: http://localhost:5173
- PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch
REST API Endpoints
| Method | Path | Description |
|---|---|---|
| GET | /api/connections |
List connections (no credentials) |
| POST | /api/db/{name}/query |
Parameterized query |
| POST | /api/db/{name}/sql |
Raw SQL / native command |
| GET | /api/db/{name}/schema |
Database schema |
| GET | /api/db/{name}/tables |
List tables/collections |
| GET | /api/db/{name}/tables/{table}/describe |
Table structure |
| GET/POST | /api/query-history |
Query history |
MCP Server
Configure in .env or Cursor MCP env:
MCP_REST_API_URL=http://localhost:8000
# Option A: bearer token (when REST_API_AUTH_MODE=oauth2)
MCP_REST_API_TOKEN=<jwt-from-/api/auth/token>
# Option B: username/password (works with basic auth; auto-fetches JWT if oauth2)
MCP_REST_API_USER=admin
MCP_REST_API_PASSWORD=changeme
Run:
db-mcp-server
Add to Cursor/Claude MCP config:
{
"mcpServers": {
"data-nexus-mcp": {
"command": "db-mcp-server",
"cwd": "/path/to/data_nexus_mcp",
"env": {
"MCP_REST_API_URL": "http://localhost:8000",
"MCP_REST_API_USER": "admin",
"MCP_REST_API_PASSWORD": "changeme"
}
}
}
}
Note: REST_API_* variables belong on the REST API process (db-rest-api), not in the MCP server config.
MCP Client
db-mcp-client # list available tools
db-mcp-client query local_sqlite "SELECT 1"
Authentication
Set REST_API_AUTH_MODE to one of:
basic— HTTP Basic Auth (default for development)oauth2— JWT bearer tokens via/api/auth/tokenldap— LDAP bind (requiresREST_API_LDAP_SERVERandREST_API_LDAP_BASE_DN)
Adding a New Driver
- Create
core_db_command/drivers/mydb.py - Subclass
BaseDriverand setdriver_type - Decorate with
@DriverRegistry.register - Import in
core_db_command/drivers/registry_loader.py
from core_db_command.base import BaseDriver, DriverRegistry
@DriverRegistry.register
class MyDBDriver(BaseDriver):
driver_type = "mydb"
async def connect(self): ...
async def disconnect(self): ...
async def query(self, query, params=None): ...
async def execute(self, command, params=None): ...
async def list_tables(self, schema=None): ...
async def describe_table(self, table, schema=None): ...
Testing
pytest tests/ -v
Security Notes
- Credentials are never returned by the REST API or MCP server
- Secrets must use
${ENV_VAR}placeholders in YAML config - All API endpoints require authentication
- Query input is validated and length-limited
Project Structure
data-nexus-mcp/
├── core_db_command/ # Core library + drivers
├── rest_api_command/ # FastAPI REST API
├── mcp_server/ # MCP server
├── mcp_client/ # MCP client
├── web-ui/ # Vue.js frontend
├── config/ # YAML connection config
├── tests/ # Unit tests
├── docker-compose.yml
├── Dockerfile
└── pyproject.toml
License
MIT
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。