- Home
- MCP servers
- Redash
Redash
- javascript
55
GitHub Stars
javascript
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"suthio-redash-mcp": {
"command": "npx",
"args": [
"-y",
"@suthio/redash-mcp"
],
"env": {
"REDASH_URL": "https://your-redash-instance.com",
"REDASH_API_KEY": "your-api-key",
"REDASH_TIMEOUT": "30000",
"REDASH_MAX_RESULTS": "1000",
"REDASH_EXTRA_HEADERS": "{\"CF-Access-Client-Id\":\"id\",\"CF-Access-Client-Secret\":\"secret\"}"
}
}
}
}This MCP server enables AI assistants to interact with Redash by exposing queries, dashboards, and visualizations as actionable resources. You can list, run, and manage Redash content through the MCP interface, empowering conversational workflows with live data insights.
How to use
You connect to the Redash MCP server from your MCP client or agent. Once connected, you can list available queries and dashboards, execute queries to retrieve results, and manage queries and visualizations directly from your assistant workflow. Use the provided tools to create, update, or archive queries, fetch data sources for query creation, and inspect dashboards and their visualizations.
How to install
Prerequisites: ensure you have Node.js version 18 or later and npm or yarn installed. You also need access to a Redash instance and a Redash API key.
Step-by-step commands to set up the MCP server locally:
# 1) Clone the repository
git clone https://github.com/suthio/redash-mcp.git
cd redash-mcp
# 2) Install dependencies
npm install
# 3) Create a configuration file with your Redash details
# Note: Ensure the file defines the required environment variables
- Build the project and start the server using the commands shown in the usage snippet:
npm run build
npm start
- Alternatively, run the server via the MCP command described for your Claude or MCP client configuration (see the configuration example in the next section).
Configuration note
To integrate with an MCP client, you typically run the server using a package runner and provide your Redash credentials through environment variables. The following example shows a complete MCP configuration you can place in your client’s MCP configuration file.
{
"mcpServers": {
"redash": {
"type": "stdio",
"name": "redash",
"command": "npx",
"args": ["-y", "@suthio/redash-mcp"],
"env": {
"REDASH_API_KEY": "your-api-key",
"REDASH_URL": "https://your-redash-instance.com"
}
}
}
}
Additional sections
Configuration notes: You may also set optional environment variables to fine-tune API interactions. Supported options include a request timeout, a maximum number of results to return, and extra HTTP headers to forward to Redash. See the environment variables section for details.
Development
Run in development mode to iterate on the MCP server codebase.
npm run dev
Testing
Unit tests and end-to-end tests are available to verify functionality. Use the following commands to run tests.
npm test
npm run e2e:test
Version history
- v1.1.0: Added query management functionality (create, update, archive) - v1.0.0: Initial release
License
MIT license.
Available tools
list-queries
List all available queries in Redash
get-query
Get details of a specific query
create-query
Create a new query in Redash
update-query
Update an existing query
archive-query
Archive (soft-delete) a query
list-data-sources
List all available data sources
execute-query
Execute a query and return results
execute-adhoc-query
Execute an ad-hoc query without saving it to Redash
get-query-results-csv
Get query results in CSV format (with optional refresh)
list-dashboards
List all available dashboards
get-dashboard
Get dashboard details and visualizations
get-visualization
Get details of a specific visualization
create-visualization
Create a new visualization for a query
update-visualization
Update an existing visualization
delete-visualization
Delete a visualization