redash-mcp-server
Enables querying and managing Redash data sources, queries, dashboards, alerts, and users through the Model Context Protocol.
README
Redash MCP Server
MCP server for the Redash API. Exposes Redash's core data operations as tools for the Model Context Protocol.
Setup
# Install dependencies
uv sync
# Set your Redash API key and URL
export REDASH_API_KEY=your_api_key
export REDASH_URL=https://redash.example.com
# Run the server
uv run python -m redash_mcp
By default the server uses the stdio transport for local MCP clients such as Claude Desktop.
Hosted MCP
The server can be deployed as a remote MCP endpoint over Streamable HTTP:
uv run python -m redash_mcp --transport streamable-http
Send your Redash API key in the request header:
Authorization: Key your_api_key
Configuration (Hosted / Streamable HTTP)
If your MCP client supports remote servers over HTTP, the JSON config should include the hosted URL and the Authorization header.
Example:
{
"mcpServers": {
"redash": {
"url": "https://your-mcp-host.com/mcp",
"headers": {
"Authorization": "Key your_api_key"
}
}
}
}
Notes:
- Replace
your_api_keywith your real Redash API key. - The header must be exactly
Authorization. - The value must include the
Keyprefix.
Claude Code (CLI)
claude mcp add --transport http redash https://your-mcp-host.com/mcp \
--header "Authorization: Key your_api_key"
Replace your_api_key with your real Redash API key.
Configuration (Claude Desktop / stdio)
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"redash": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/redash-mcp-server", "run", "python", "-m", "redash_mcp"],
"env": {
"REDASH_API_KEY": "your_api_key",
"REDASH_URL": "https://redash.example.com"
}
}
}
}
Available Tools
| Resource | Tools |
|---|---|
| Queries | list_queries, get_query, create_query, update_query, search_queries, get_recent_queries, archive_query, refresh_query |
| Dashboards | list_dashboards, get_dashboard, create_dashboard, update_dashboard |
| Data Sources | list_data_sources, get_data_source, get_data_source_schema, check_data_source_connection |
| Query Results | get_query_result, execute_query |
| Users | list_users, get_user |
| Alerts | list_alerts, get_alert, create_alert |
| Visualizations | list_query_visualizations |
Environment Variables
| Variable | Description | Default |
|---|---|---|
REDASH_API_KEY |
Redash API key (required for stdio transport) | — |
REDASH_URL |
Base URL of your Redash instance | http://localhost:5000 |
REDASH_MCP_TRANSPORT |
Transport type (stdio or streamable-http) |
stdio |
REDASH_MCP_HOST |
Host to bind HTTP server | 127.0.0.1 |
REDASH_MCP_PORT |
Port for HTTP server | 8000 |
REDASH_MCP_STREAMABLE_HTTP_PATH |
HTTP path for MCP endpoint | /mcp |
Docker
# Build the image
docker build -t redash-mcp .
docker run -i --rm \
-e REDASH_API_KEY=your_api_key \
-e REDASH_URL=https://redash.example.com \
redash-mcp
Configuration (Claude Desktop with Docker / stdio)
{
"mcpServers": {
"redash": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "REDASH_API_KEY", "-e", "REDASH_URL", "redash-mcp"],
"env": {
"REDASH_API_KEY": "your_api_key",
"REDASH_URL": "https://redash.example.com"
}
}
}
}
Development
# Install with dev dependencies
uv sync --extra dev
# Run tests
uv run pytest tests/ -v
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。