Amazon Bedrock AgentCore Runtime にホストした aws-dataprocessing-mcp-server を Amazon Quick から自然言語でデータレイクを操作してみた

import uvicorn
from mcp.server.fastmcp import FastMCP
from mcp.server.transport_security import TransportSecuritySettings
from starlette.routing import Route

_original_init = FastMCP.__init__

def _patched_init(self, *args, **kwargs):
    kwargs.setdefault(
        "transport_security",
        TransportSecuritySettings(enable_dns_rebinding_protection=False),
    )
    _original_init(self, *args, **kwargs)

FastMCP.__init__ = _patched_init

_original_run = FastMCP.run

def _patched_run(self, transport=None, **kwargs):
    self.settings.host = "0.0.0.0"
    self.settings.port = 8000
    self.settings.stateless_http = True

    if transport == "streamable-http" or transport is None:
        app = self.streamable_http_app()
        app.router.redirect_slashes = False
        existing = next(
            r for r in app.router.routes if isinstance(r, Route) and r.path == "/mcp"
        )
        app.router.routes.append(
            Route("/mcp/", endpoint=existing.endpoint, methods=existing.methods)
        )
        uvicorn.run(app, host="0.0.0.0", port=8000, log_level="info")
        return
    return _original_run(self, transport=transport)

FastMCP.run = _patched_run

from awslabs.aws_dataprocessing_mcp_server.server import main  # noqa: E402

if __name__ == "__main__":
    main()

FROM --platform=linux/arm64 python:3.12-slim

ENV PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1

WORKDIR /app

COPY requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -r /app/requirements.txt

COPY server_http.py /app/server_http.py

RUN groupadd -r app && useradd -r -g app -d /home/app -m app
USER app

EXPOSE 8000

ENTRYPOINT ["python", "/app/server_http.py"]

awslabs.aws-dataprocessing-mcp-server==0.1.31
mcp[cli]==1.23.0
uvicorn==0.32.0

podman build --platform linux/arm64 -t dataprocessing-mcp-agentcore:v0.4 .

$ curl -s -X POST "http://localhost:8000/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"0.1"}}}' | head -3

event: message
data: {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2025-06-18","capabilities":{...},"serverInfo":{"name":"awslabs.aws-dataprocessing-mcp-server","version":"1.23.0"}, ...}}

aws cognito-idp create-user-pool \
  --pool-name dp-mcp-agentcore-pool \
  --policies '{"PasswordPolicy":{"MinimumLength":12,"RequireUppercase":true,"RequireLowercase":true,"RequireNumbers":true,"RequireSymbols":true}}' \
  --region ap-northeast-1

aws cognito-idp create-resource-server \
  --user-pool-id ap-northeast-1_ogeMbwGMK \
  --identifier dp-mcp \
  --name "Dataprocessing MCP Resource Server" \
  --scopes \
    ScopeName=read,ScopeDescription="Read data processing resources" \
    ScopeName=write,ScopeDescription="Write data processing resources" \
  --region ap-northeast-1

aws cognito-idp create-user-pool-domain \
  --user-pool-id ap-northeast-1_ogeMbwGMK \
  --domain dp-mcp-1f6b687c \
  --region ap-northeast-1

aws cognito-idp create-user-pool-client \
  --user-pool-id ap-northeast-1_ogeMbwGMK \
  --client-name dp-mcp-m2m-client \
  --generate-secret \
  --allowed-o-auth-flows client_credentials \
  --allowed-o-auth-scopes "dp-mcp/read" "dp-mcp/write" \
  --allowed-o-auth-flows-user-pool-client \
  --supported-identity-providers COGNITO \
  --region ap-northeast-1

$ aws bedrock-agentcore-control create-agent-runtime \
  --agent-runtime-name dp_mcp_agentcore \
  --agent-runtime-artifact 'containerConfiguration={containerUri=613820096496.dkr.ecr.ap-northeast-1.amazonaws.com/dataprocessing-mcp-agentcore:v0.4}' \
  --network-configuration 'networkMode=PUBLIC' \
  --protocol-configuration 'serverProtocol=MCP' \
  --role-arn arn:aws:iam::613820096496:role/AgentCoreRuntimeRole-DpMcp \
  --authorizer-configuration 'customJWTAuthorizer={discoveryUrl=https://cognito-idp.ap-northeast-1.amazonaws.com/ap-northeast-1_ogeMbwGMK/.well-known/openid-configuration,allowedClients=[38gvcra4aiq2kof9tim48ujoqb]}' \
  --environment-variables 'AWS_REGION=ap-northeast-1,FASTMCP_LOG_LEVEL=INFO' \
  --region ap-northeast-1

{
  "agentRuntimeArn": "arn:aws:bedrock-agentcore:ap-northeast-1:613820096496:runtime/dp_mcp_agentcore-O8HEgzH8Fj",
  "agentRuntimeId": "dp_mcp_agentcore-O8HEgzH8Fj",
  "agentRuntimeVersion": "1",
  "status": "CREATING"
}

import asyncio, base64, json, urllib.parse, urllib.request
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

REGION = "ap-northeast-1"
ARN = "arn:aws:bedrock-agentcore:ap-northeast-1:613820096496:runtime/dp_mcp_agentcore-O8HEgzH8Fj"
DOMAIN = "dp-mcp-1f6b687c"
CLIENT_ID = "..."
CLIENT_SECRET = "..."

def get_jwt():
    body = urllib.parse.urlencode({"grant_type": "client_credentials",
                                   "scope": "dp-mcp/read dp-mcp/write"}).encode()
    creds = base64.b64encode(f"{CLIENT_ID}:{CLIENT_SECRET}".encode()).decode()
    req = urllib.request.Request(
        f"https://{DOMAIN}.auth.{REGION}.amazoncognito.com/oauth2/token",
        data=body,
        headers={"Authorization": f"Basic {creds}",
                 "Content-Type": "application/x-www-form-urlencoded"},
    )
    return json.loads(urllib.request.urlopen(req).read())["access_token"]

async def main():
    token = get_jwt()
    url = (f"https://bedrock-agentcore.{REGION}.amazonaws.com/runtimes/"
           f"{urllib.parse.quote(ARN, safe='')}/invocations?qualifier=DEFAULT")
    headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
    async with streamablehttp_client(url, headers, timeout=120) as (r, w, _):
        async with ClientSession(r, w) as session:
            await session.initialize()
            tools = await session.list_tools()
            print(f"tool count: {len(tools.tools)}")
            result = await session.call_tool(
                "manage_aws_glue_databases",
                {"operation": "list-databases", "region_name": REGION},
            )
            for c in result.content:
                if c.type == "text":
                    print(c.text[:600])

asyncio.run(main())

tool count: 36
Successfully listed 7 databases
{"databases":[{"name":"default", ...},{"name":"qsdemo_dev", ...},{"name":"qsdemo_iot", ...},{"name":"qsdemo_sandbox", ...},{"name":"quick_workshop", ...}], "count":7, ...}

=== manage_aws_athena_databases_and_tables (list-databases) ===
{"database_list":[{"Name":"default"},{"Name":"ishikawa"},{"Name":"iwasa"},{"Name":"qsdemo_dev"},{"Name":"qsdemo_iot"},{"Name":"qsdemo_sandbox"},{"Name":"quick_workshop"}],"count":7}