CSV MCP

Query CSV data from your MCP client.

Import a CSV file through Data Connector to create a managed table. Your compatible MCP client can then inspect its columns and run bounded, read-only queries.

1. Import your CSV

Sign in at dataconnector.ai, choose a workspace, and upload the file. Data Connector sends the upload through its API, reads the header, infers supported column types, and creates a queryable table.

2. Add Data Connector to your client

Use the hosted remote MCP endpoint:

https://dataconnector.ai/api/mcp

Complete OAuth and authorize the workspace containing your imported table.

3. Ask about the table

Try: List my tables, describe the imported CSV table, then show me five example rows. Data Connector exposes bounded tools for table discovery, schema inspection, and read-only SQL.

Managed after import

Your MCP client does not receive a local file path or unrestricted database connection. It queries the managed table through Data Connector's workspace permissions and API.

Frequently asked questions

Can an MCP client query a CSV file?

Yes. Import the CSV through Data Connector, then authorize its workspace from any compatible remote MCP client.

Does Data Connector read a path on my computer?

No. You upload the file through the authenticated Data Connector import flow. MCP tools query the resulting managed table.

Does Data Connector infer CSV column types?

Yes. It reads the CSV header and infers supported column types when creating the table.

Import a CSV Set up MCP