Connect an Astra DB MCP server to Langflow
Use the MCP server component to connect Langflow to a Datastax Astra DB MCP server.
-
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 DB application token with the Database Administrator role. For more information, see Generate an application token for a database.
-
Create a Simple agent starter project.
-
Remove the URL tool and replace it with an MCP server component. The flow should look like this:
-
In the MCP server component, in the MCP server field, add the following code to connect to an Astra DB MCP server:
_10npx -y @datastax/astra-db-mcp -
In the MCP server component, in the Env fields, add variables for
ASTRA_DB_APPLICATION_TOKEN
andASTRA_DB_API_ENDPOINT
with the values from your Astra database.importantLangflow passes environment variables from the
.env
file to MCP, but not global variables declared in the UI. To add the values forASTRA_DB_APPLICATION_TOKEN
andASTRA_DB_API_ENDPOINT
as global variables, add them to Langflow's.env
file at startup. For more information, see global variables._10ASTRA_DB_APPLICATION_TOKEN=AstraCS:... -
To add another variable, click Add More.
_10ASTRA_DB_API_ENDPOINT=https://...-us-east-2.apps.astra.datastax.com -
In the Agent component, add your OpenAI API key.
-
Open the Playground, and then ask the agent,
What collections are available?
Since Langflow is connected to your Astra DB database through the MCP, the agent chooses the correct tool and connects to your database to retrieve the answer.
_10The available collections in your database are:_10collection_002_10hardware_requirements_10load_collection_10nvidia_collection_10software_requirements