View a markdown version of this page

Daftar template sumber daya di AgentCore gateway - Batuan Dasar Amazon AgentCore

Daftar template sumber daya di AgentCore gateway

Untuk mencantumkan semua templat sumber daya yang tersedia yang disediakan AgentCore gateway, buat permintaan POST ke titik akhir MCP gateway dan tentukan resources/templates/list sebagai metode di badan permintaan:

POST /mcp HTTP/1.1 Host: ${GatewayEndpoint} Content-Type: application/json Authorization: ${Authorization header} ${RequestBody}

Ganti nilai-nilai berikut:

catatan

Untuk daftar parameter yang didukung secara opsionalresources/templates/list, lihat params objek di badan permintaan di Resources dalam dokumentasi Protokol Konteks Model. Di bagian atas halaman di sebelah bilah pencarian, Anda dapat memilih versi MCP yang dokumentasinya ingin Anda lihat. Pastikan versi tersebut didukung oleh Amazon Bedrock AgentCore.

Respons menampilkan daftar template sumber daya yang tersedia dengan templat URI, nama, deskripsi, dan tipe MIME mereka.

catatan

Template sumber daya menggunakan templat URI RFC 6570 untuk mendeskripsikan sumber daya berparameter. Klien dapat mengisi parameter template untuk membangun URI sumber daya konkret untuk digunakan. resources/read Misalnya, template users://{user_id}/profile dapat diperluas keusers://123/profile.

Sampel kode untuk mencantumkan templat sumber daya

Untuk melihat contoh daftar templat sumber daya yang tersedia di gateway, pilih salah satu metode berikut:

contoh
Python requests package
  1. import requests import json def list_resource_templates(gateway_url, access_token): headers = { "Content-Type": "application/json", "Authorization": f"Bearer {access_token}" } payload = { "jsonrpc": "2.0", "id": "list-resource-templates-request", "method": "resources/templates/list" } response = requests.post(gateway_url, headers=headers, json=payload) return response.json() # Example usage gateway_url = "https://${GatewayEndpoint}/mcp" # Replace with your actual gateway endpoint access_token = "${AccessToken}" # Replace with your actual access token templates = list_resource_templates(gateway_url, access_token) print(json.dumps(templates, indent=2))
MCP Client
  1. import asyncio from mcp import ClientSession from mcp.client.streamable_http import streamablehttp_client async def execute_mcp( url, token, headers=None ): default_headers = { "Authorization": f"Bearer {token}" } headers = {**default_headers, **(headers or {})} async with streamablehttp_client( url=url, headers=headers, ) as ( read_stream, write_stream, callA, ): async with ClientSession(read_stream, write_stream) as session: # 1. Perform initialization handshake print("Initializing MCP...") _init_response = await session.initialize() print(f"MCP Server Initialize successful! - {_init_response}") # 2. List available resource templates print("Listing resource templates...") cursor = True templates = [] while cursor: next_cursor = cursor if isinstance(cursor, bool): next_cursor = None list_templates_response = await session.list_resource_templates(next_cursor) templates.extend(list_templates_response.resourceTemplates) cursor = list_templates_response.nextCursor if templates: for template in templates: print(f"{template.uriTemplate} - {template.name}") print(f"Total resource templates: {len(templates)}") async def main(): url = "https://${GatewayEndpoint}/mcp" token = "your_bearer_token_here" # Optional additional headers additional_headers = { "Content-Type": "application/json", } await execute_mcp( url=url, token=token, headers=additional_headers ) # Run the async function if __name__ == "__main__": asyncio.run(main())
Strands MCP Client
  1. # NOTE: Strands SDK resource template support may vary. Use the MCP Client # approach above for the most reliable resources/templates/list implementation. from strands.tools.mcp.mcp_client import MCPClient from mcp.client.streamable_http import streamablehttp_client def create_streamable_http_transport(mcp_url: str, access_token: str): return streamablehttp_client(mcp_url, headers={"Authorization": f"Bearer {access_token}"}) def run_agent(mcp_url: str, access_token: str): mcp_client = MCPClient(lambda: create_streamable_http_transport(mcp_url, access_token)) with mcp_client: result = mcp_client.list_resource_templates_sync() print(f"Found the following templates: {[t.uriTemplate for t in result.resourceTemplates]}") run_agent(<MCP URL>, <Access token>)
LangGraph MCP Client
  1. # NOTE: LangGraph MCP adapter resource template support may vary. Use the MCP # Client approach above for the most reliable implementation. import asyncio from mcp import ClientSession from mcp.client.streamable_http import streamablehttp_client async def list_resource_templates(url, token): headers = {"Authorization": f"Bearer {token}"} async with streamablehttp_client(url=url, headers=headers) as ( read_stream, write_stream, callA ): async with ClientSession(read_stream, write_stream) as session: await session.initialize() response = await session.list_resource_templates() for template in response.resourceTemplates: print(f"{template.uriTemplate} - {template.name}") asyncio.run(list_resource_templates("https://${GatewayEndpoint}/mcp", "${AccessToken}"))