Connect an Astra DB MCP server to Langflow - Langflow

import Icon from "@site/src/components/icon"; import PartialMcpNodeTip from '@site/docs/_partial-mcp-node-tip.mdx'; import McpIcon from '@site/static/logos/mcp-icon.svg';

This guide demonstrates how to use Langflow as an MCP client by using the MCP Tools component to run a DataStax Astra DB MCP server in an agent flow.

Install an LTS release of Node.js.

Create an OpenAI API key.
Create an Astra DB Serverless (vector) database, if you don't already have one.
Get your database's Astra DB API endpoint and an Astra application token with the Database Administrator role. For more information, see Generate an application token for a database.
To follow along with this guide, create a flow based on the Simple Agent template.

You can also use an existing flow or create a blank flow.
Remove the URL tool from the flow.
Register the Astra DB MCP server from the <McpIcon /> MCP sidebar and add MCP Tools to the canvas. Use the following values:
1. In the Name field, enter a name for the MCP server.
2. In the Command field, add the following code to connect to an Astra DB MCP server:
  bash
```
npx -y @datastax/astra-db-mcp
```
3. In the Environment Variables fields, add variables for ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT with the values from your Astra database.
  
  :::info Environment variables declared in your Langflow .env file can be referenced in your MCP server commands, but you cannot reference global variables declared in Langflow.
  
  If you want to use variables for ASTRA_DB_APPLICATION_TOKEN and ASTRA_DB_API_ENDPOINT, add them to Langflow's .env file, and then restart Langflow. For more information, see global variables. :::
  
  Add each variable separately. To add another variable field click <Icon name="Plus" aria-hidden="true"/> Add More.
  bash
```
ASTRA_DB_APPLICATION_TOKEN=AstraCS:...
```
  bash
```
ASTRA_DB_API_ENDPOINT=https://...-us-east-2.apps.astra.datastax.com
```
In the Agent component, add your OpenAI API key.

The default model is an OpenAI model. If you want to use a different model, edit the Model Provider, Model Name, and API Key fields accordingly.
Open the Playground, and then ask the agent, What collections are available?

Since Langflow is connected to your Astra DB database through the MCP server, the agent chooses the correct tool and connects to your database to retrieve the answer. For example:
text
```
The available collections in your database are:
collection_002
hardware_requirements
load_collection
nvidia_collection
software_requirements
```