Let AI clients call AskTable through MCP

The standalone container's HTTP transport accepts any path without requiring the /mcp/ prefix. The all-in-one image exposes only /mcp/ externally; nginx strips the prefix before forwarding to 8690.

Streamable HTTP configuration (field names depend on your client):

{
  "mcpServers": {
    "asktable": {
      "type": "http",
      "url": "https://mcp.asktable.com/",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

The Authorization header is required. The server creates an independent client instance for each request and does not retain state across tenants.

After connecting, ask the client to list tools; you should see 43. They are grouped by domain below:

List tools accept page and size (size is capped at 200); omitted values use backend defaults.

Have the client call chat_ask to ask a question. For multiple turns, use chat_followup to continue the previous conversation. If the client provides progressToken, these tools send progress notifications between each poll.

Delete tools (*_delete) require confirm to be true; omitting it is treated as a parameter error.

For standalone debugging or MCP Inspector, start stdio in the mcp/ directory:

bun src/main.ts --stdio

In stdio mode, the Key comes from environment variables:

export ASKTABLE_API_URL='https://<your-AskTable-site>'
export ASKTABLE_API_KEY='YOUR_API_KEY'

The server uses ASKTABLE_API_URL to target AskTable's API, defaulting to https://api.asktable.com. In the all-in-one image it is set to http://127.0.0.1:8688, using localhost within the same container.

Client configuration files are often synchronized or backed up. Use the client's secret management to inject Authorization in production rather than leaving the Key in plaintext in a configuration repository. If a Key leaks, immediately delete and recreate it in “Settings” → “API-Key.”