> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bridger.kr/llms.txt
> Use this file to discover all available pages before exploring further.

# Call your first tool

> Make your first call to a tool registered with Bridger using MCP JSON-RPC.

This page shows what request returns what response right after you connect to the Bridger Gateway.
Pick one tool and trace the input → output flow; from then on, you can call any tool with the same
pattern.

## Prerequisites

* [API key issued](/en/guides/api-keys)
* Key stored in the `DATA_BRIDGE_API_KEY` environment variable

```bash theme={null}
export DATA_BRIDGE_API_KEY="dk_live_..."
```

## 1. List registered tools

`tools/list` returns the **metadata of every MCP tool** loaded into Bridger (`name`, `description`,
`inputSchema`).

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST https://mcp.datari.kr/mcp \
    -H "x-api-key: $DATA_BRIDGE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
  ```

  ```javascript Node.js theme={null}
  const res = await fetch("https://mcp.datari.kr/mcp", {
    method: "POST",
    headers: {
      "x-api-key": process.env.DATA_BRIDGE_API_KEY,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      jsonrpc: "2.0",
      id: 1,
      method: "tools/list",
    }),
  });
  console.log(await res.json());
  ```

  ```python Python theme={null}
  import os, requests
  r = requests.post(
      "https://mcp.datari.kr/mcp",
      headers={
          "x-api-key": os.environ["DATA_BRIDGE_API_KEY"],
          "Content-Type": "application/json",
      },
      json={"jsonrpc": "2.0", "id": 1, "method": "tools/list"},
  )
  print(r.json())
  ```
</CodeGroup>

The response includes tools with the following structure.

```json theme={null}
{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "tools": [
      {
        "name": "getultrashortcast",
        "description": "KMA ultra-short-term forecast — data.go.kr OpenAPI",
        "inputSchema": {
          "type": "object",
          "properties": {
            "searchKeyword": { "type": "string", "description": "Search keyword" },
            "pageNo": { "type": "integer", "description": "Page number" },
            "numOfRows": { "type": "integer", "description": "Results per page" }
          }
        }
      }
    ]
  }
}
```

## 2. Run a tool

Pick one tool and run it with `tools/call`. The example is an ultra-short-term forecast for Seoul.

```bash theme={null}
curl -X POST https://mcp.datari.kr/mcp \
  -H "x-api-key: $DATA_BRIDGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
      "name": "getultrashortcast",
      "arguments": {
        "searchKeyword": "Seoul",
        "numOfRows": 10
      }
    }
  }'
```

## 3. Receive real-time events over SSE

For long-running tools or streaming responses, subscribe to the SSE endpoint (`/mcp/sse`).

```bash theme={null}
curl -N https://mcp.datari.kr/mcp/sse \
  -H "x-api-key: $DATA_BRIDGE_API_KEY"
```

A `gateway/toolResult` event is delivered to your client for each tool execution.

## Next steps

<CardGroup cols={2}>
  <Card title="Connect to Claude" icon="comment" href="/en/guides/claude">
    Let Claude call the same tools above in natural language.
  </Card>

  <Card title="API Reference" icon="book" href="/en/api-reference/introduction">
    Full JSON-RPC and SSE spec, plus error codes.
  </Card>
</CardGroup>