List Tools

Lists all tools available for a specific remote MCP server in various AI model formats.

This eliminates the need for manual MCP code implementation and format conversion. Under the hood, Klavis instantiates an MCP client and establishes a connection with the remote MCP server to retrieve available tools.

POST /mcp-server/list-tools

List Tools

cURL

curl --request POST \
  --url https://api.klavis.ai/mcp-server/list-tools \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "serverUrl": "<string>",
  "connectionType": "StreamableHttp",
  "format": "mcp_native",
  "headers": {}
}
'

200

{
  "success": true,
  "format": "openai",
  "tools": [
    "<unknown>"
  ],
  "error": "<string>"
}

Authorizations

Authorization · string · header · required

Your Klavis AI API key.

Body

application/json

serverUrl · string · required

The full URL for connecting to the MCP server

connectionType · enum<string> · default: StreamableHttp

The connection type to use for the MCP server. Default is STREAMABLE_HTTP.

Available options: SSE, StreamableHttp

format · enum<string> · default: mcp_native

The format to return tools in. Default is MCP Native format for maximum compatibility.

Available options: openai, anthropic, gemini, mcp_native

headers · Headers · object | null

Optional HTTP headers to include when connecting to the server

Show child attributes

Response

200

application/json

Successful Response

success · boolean · required

Whether the list tools request was successful

format · enum<string> · required

The format of the returned tools

Available options: openai, anthropic, gemini, mcp_native

tools · any[] | null

List of tools in the requested format

error · string | null

Error message, if the request failed