Implémenter l'API Game et le serveur MCP Inventory
Tâche 1 : Implémenter l’API Game
Section intitulée « Tâche 1 : Implémenter l’API Game »Nous allons implémenter les API suivantes dans cette section :
saveGame- créer ou mettre à jour une partie.queryGames- retourner une liste paginée des parties précédemment sauvegardées.queryInventory- retourner une liste paginée des objets dans l’inventaire d’un joueur.queryActions- retourner l’historique de conversation pour une partie donnée.
Schéma de l’API
Section intitulée « Schéma de l’API »Pour définir nos entrées et sorties d’API, créons notre schéma en utilisant Zod dans le fichier packages/game-api/src/schema/index.ts comme suit :
import { z } from 'zod';
export const QueryInputSchema = z.object({ cursor: z.string().optional(), limit: z.number().optional().default(100),});export type IQueryInput = z.TypeOf<typeof QueryInputSchema>;
export const ActionSchema = z.object({ role: z.enum(['user', 'assistant']), content: z.string(), messageId: z.number(),});export type IAction = z.TypeOf<typeof ActionSchema>;
export const GameSchema = z.object({ playerName: z.string(), genre: z.enum(['zombie', 'superhero', 'medieval']), lastUpdated: z.iso.datetime(),});export type IGame = z.TypeOf<typeof GameSchema>;
export const ItemSchema = z.object({ playerName: z.string(), itemName: z.string(), emoji: z.string().optional(), lastUpdated: z.iso.datetime(), quantity: z.number(),});export type IItem = z.TypeOf<typeof ItemSchema>;
export const createPaginatedQueryOutput = <ItemType extends z.ZodTypeAny>( itemSchema: ItemType,) => { return z.object({ items: z.array(itemSchema), cursor: z.string().nullable(), });};export * from './echo.js'import { z } from 'zod';
export const QueryInputSchema = z.object({ cursor: z.string().optional(), limit: z.number().optional().default(100),});export type IQueryInput = z.TypeOf<typeof QueryInputSchema>;
export const ActionSchema = z.object({ role: z.enum(['user', 'assistant']), content: z.string(), messageId: z.number(),});export type IAction = z.TypeOf<typeof ActionSchema>;
export const GameSchema = z.object({ playerName: z.string(), genre: z.enum(['zombie', 'superhero', 'medieval']), lastUpdated: z.iso.datetime(),});export type IGame = z.TypeOf<typeof GameSchema>;
export const ItemSchema = z.object({ playerName: z.string(), itemName: z.string(), emoji: z.string().optional(), lastUpdated: z.iso.datetime(), quantity: z.number(),});export type IItem = z.TypeOf<typeof ItemSchema>;
export const createPaginatedQueryOutput = <ItemType extends z.ZodTypeAny>( itemSchema: ItemType,) => { return z.object({ items: z.array(itemSchema), cursor: z.string().nullable(), });};Supprimez le fichier packages/game-api/src/schema/echo.ts car nous ne l’utiliserons pas dans ce projet.
Modélisation des entités
Section intitulée « Modélisation des entités »Voici le diagramme ER de notre application.
Le générateur ts#dynamodb a configuré ElectroDB, que nous utiliserons pour modéliser nos données. Nous allons persister l’historique de conversation dans S3, donc nous ajoutons une dépendance au client S3 :
pnpm add @aws-sdk/client-s3@3.1111.0 --filter game-apiyarn workspace @dungeon-adventure/game-api add @aws-sdk/client-s3@3.1111.0npm install --legacy-peer-deps @aws-sdk/client-s3@3.1111.0 -w packages/game-apibun add @aws-sdk/client-s3@3.1111.0 --cwd packages/game-apiRemplacez l’entité d’exemple générée dans packages/dungeon-db/src/entities/index.ts par nos entités Game et Inventory, et supprimez packages/dungeon-db/src/entities/example.ts :
import { Entity } from 'electrodb';import { getDynamoDBClient, resolveTableName } from '../client.js';
export const createGameEntity = async () => new Entity( { model: { entity: 'Game', version: '1', service: 'game', }, attributes: { playerName: { type: 'string', required: true, readOnly: true }, genre: { type: 'string', required: true, readOnly: true }, lastUpdated: { type: 'string', required: true, default: () => new Date().toISOString(), }, }, indexes: { primary: { pk: { field: 'pk', composite: ['playerName'] }, sk: { field: 'sk', composite: [] }, }, }, }, { client: getDynamoDBClient(), table: await resolveTableName() }, );
export const createInventoryEntity = async () => new Entity( { model: { entity: 'Inventory', version: '1', service: 'game', }, attributes: { playerName: { type: 'string', required: true, readOnly: true }, lastUpdated: { type: 'string', required: true, default: () => new Date().toISOString(), }, itemName: { type: 'string', required: true, }, emoji: { type: 'string', required: false, }, quantity: { type: 'number', required: true, }, }, indexes: { primary: { pk: { field: 'pk', composite: ['playerName'] }, sk: { field: 'sk', composite: ['itemName'] }, }, }, }, { client: getDynamoDBClient(), table: await resolveTableName() }, );ElectroDB nous permet non seulement de définir nos types, mais peut également fournir des valeurs par défaut pour certaines valeurs comme les horodatages. De plus, ElectroDB suit la conception à table unique qui est la meilleure pratique lors de l’utilisation de DynamoDB.
Définition de nos procédures
Section intitulée « Définition de nos procédures »Pour implémenter les méthodes de l’API, effectuez les modifications suivantes dans packages/game-api/src/procedures :
import { createGameEntity } from '@dungeon-adventure/dungeon-db';import { GameSchema, IGame, QueryInputSchema, createPaginatedQueryOutput,} from '../schema/index.js';import { publicProcedure } from '../init.js';
export const queryGames = publicProcedure .input(QueryInputSchema) .output(createPaginatedQueryOutput(GameSchema)) .query(async ({ input }) => { const gameEntity = await createGameEntity(); const result = await gameEntity.scan.go({ cursor: input.cursor, count: input.limit, });
return { items: result.data as IGame[], cursor: result.cursor, }; });
export const saveGame = publicProcedure .input(GameSchema.omit({ lastUpdated: true })) .output(GameSchema) .mutation(async ({ input }) => { const gameEntity = await createGameEntity();
const result = await gameEntity.put(input).go(); return result.data as IGame; });import { ItemSchema, QueryInputSchema, createPaginatedQueryOutput,} from '../schema/index.js';import { publicProcedure } from '../init.js';import { z } from 'zod';import { createInventoryEntity } from '@dungeon-adventure/dungeon-db';
export const queryInventory = publicProcedure .input(QueryInputSchema.extend({ playerName: z.string() })) .output(createPaginatedQueryOutput(ItemSchema)) .query(async ({ input }) => { const inventoryEntity = await createInventoryEntity(); const result = await inventoryEntity.query .primary({ playerName: input.playerName }) .go({ cursor: input.cursor, count: input.limit });
return { items: result.data, cursor: result.cursor, }; });import { publicProcedure } from '../init.js';import { ActionSchema, IAction } from '../schema/index.js';import { z } from 'zod';import { S3Client, ListObjectsV2Command, GetObjectCommand,} from '@aws-sdk/client-s3';import { getAppConfig } from '@aws-lambda-powertools/parameters/appconfig';import { readFile, readdir } from 'node:fs/promises';import { join, resolve } from 'node:path';
const resolveSessionsBucket = async (): Promise<string> => { const agentcore = await getAppConfig('agentcore', { application: process.env.RUNTIME_CONFIG_APP_ID!, environment: 'default', transform: 'json', }); const bucket = (agentcore as Record<string, any>).agentRuntimes?.StoryAgent ?.session?.bucketName; if (!bucket) throw new Error( 'StoryAgent session bucket not found in runtime config', ); return bucket;};
const s3 = new S3Client();const LOCAL_SESSION_STORAGE_DIR = '../../tmp/agents/strands/story-agent';
// Matches ``session_<sessionId>/agents/agent_<agentId>/messages/message_<idx>.json``// written by ``strands.session.S3SessionManager`` on the agent side. We only// ever care about the default agent id ``default`` that Strands uses when// none is set explicitly, so hard-code the path prefix the UI needs to list.const messagesPrefix = (sessionId: string) => `session_${sessionId}/agents/agent_default/messages/`;
const messageIndex = (pathOrKey: string): number => { const match = pathOrKey.match(/message_(\d+)\.json$/); return match ? Number(match[1]) : Number.MAX_SAFE_INTEGER;};
const toAction = (body: any): IAction | undefined => { const message = body.redact_message ?? body.message; const role = message?.role; if (role !== 'user' && role !== 'assistant') return undefined; const text = Array.isArray(message.content) ? message.content .filter((b: any) => typeof b?.text === 'string') .map((b: any) => b.text) .join('') : String(message.content ?? ''); if (!text) return undefined; return { role, content: text, messageId: body.message_id };};
const readLocalActions = async (sessionId: string): Promise<IAction[]> => { const baseDir = resolve(LOCAL_SESSION_STORAGE_DIR); const messagesDir = resolve(baseDir, messagesPrefix(sessionId)); if (!messagesDir.startsWith(`${baseDir}/`)) { throw new Error('Invalid session id'); }
let files: string[]; try { files = await readdir(messagesDir); } catch (error: any) { if (error?.code === 'ENOENT') return []; throw error; }
const actions: IAction[] = []; for (const file of files .filter((f) => f.endsWith('.json')) .sort((a, b) => messageIndex(a) - messageIndex(b))) { const body = JSON.parse(await readFile(join(messagesDir, file), 'utf8')); const action = toAction(body); if (action) actions.push(action); } return actions;};
const readS3Actions = async (sessionId: string): Promise<IAction[]> => { const bucket = await resolveSessionsBucket(); const list = await s3.send( new ListObjectsV2Command({ Bucket: bucket, Prefix: messagesPrefix(sessionId), }), ); const keys = (list.Contents ?? []) .map((o) => o.Key!) .filter((k) => k.endsWith('.json')) .sort((a, b) => messageIndex(a) - messageIndex(b));
const actions: IAction[] = []; for (const key of keys) { const obj = await s3.send( new GetObjectCommand({ Bucket: bucket, Key: key }), ); const body = JSON.parse(await obj.Body!.transformToString()); const action = toAction(body); if (action) actions.push(action); } return actions;};
export const queryActions = publicProcedure .input(z.object({ sessionId: z.string() })) .output(z.object({ items: z.array(ActionSchema) })) .query(async ({ input }) => { const actions = process.env.LOCAL_DEV === 'true' ? await readLocalActions(input.sessionId) : await readS3Actions(input.sessionId); return { items: actions }; });Supprimez le fichier echo.ts (de packages/game-api/src/procedures) car nous ne l’utiliserons pas dans ce projet.
Configuration du routeur
Section intitulée « Configuration du routeur »Après avoir défini nos procédures, pour les intégrer dans notre API, mettez à jour le fichier suivant :
import { t } from './init.js';import { queryActions } from './procedures/actions.js';import { queryGames, saveGame } from './procedures/games.js';import { queryInventory } from './procedures/inventory.js';
export const router = t.router;
export const appRouter = router({ actions: router({ query: queryActions, }), games: router({ query: queryGames, save: saveGame, }), inventory: router({ query: queryInventory, }),});
export type AppRouter = typeof appRouter;import { echo } from './procedures/echo.js';import { t } from './init.js';import { queryActions } from './procedures/actions.js';import { queryGames, saveGame } from './procedures/games.js';import { queryInventory } from './procedures/inventory.js';
export const router = t.router;
export const appRouter = router({ echo, actions: router({ query: queryActions, }), games: router({ query: queryGames, save: saveGame, }), inventory: router({ query: queryInventory, }),});
export type AppRouter = typeof appRouter;Tâche 2 : Créer un serveur MCP Inventory
Section intitulée « Tâche 2 : Créer un serveur MCP Inventory »Créons un serveur MCP qui permettra à notre agent de gérer les objets dans l’inventaire d’un joueur.
Nous allons définir les outils suivants pour notre agent :
list-inventory-itemspour récupérer les objets actuels de l’inventaire du joueuradd-to-inventorypour ajouter des objets à l’inventaire du joueurremove-from-inventorypour retirer des objets de l’inventaire du joueur
Pour gagner du temps, nous allons définir tous les outils en ligne :
import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';import z from 'zod';import { createInventoryEntity } from '@dungeon-adventure/dungeon-db';
/** * Create the MCP Server */export const createServer = async () => { const server = new McpServer({ name: 'inventory-mcp-server', version: '1.0.0', });
server.registerTool( 'list-inventory-items', { description: "List items in the player's inventory. Leave cursor blank unless you are requesting subsequent pages", inputSchema: { playerName: z.string(), cursor: z.string().optional(), }, }, async ({ playerName }) => { const inventory = await createInventoryEntity(); const results = await inventory.query .primary({ playerName, }) .go();
return { content: [{ type: 'text' as const, text: JSON.stringify(results) }], }; }, );
server.registerTool( 'add-to-inventory', { description: "Add an item to the player's inventory. Quantity defaults to 1 if omitted.", inputSchema: { playerName: z.string(), itemName: z.string(), emoji: z.string(), quantity: z.number().optional().default(1), }, }, async ({ playerName, itemName, emoji, quantity = 1 }) => { const inventory = await createInventoryEntity(); await inventory .put({ playerName, itemName, quantity, emoji, }) .go();
return { content: [ { type: 'text' as const, text: `Added ${itemName} (x${quantity}) to inventory`, }, ], }; }, );
server.registerTool( 'remove-from-inventory', { description: "Remove an item from the player's inventory. If quantity is omitted, all items are removed.", inputSchema: { playerName: z.string(), itemName: z.string(), quantity: z.number().optional(), }, }, async ({ playerName, itemName, quantity }) => { const inventory = await createInventoryEntity();
// If quantity is omitted, remove the entire item if (quantity === undefined) { try { await inventory.delete({ playerName, itemName }).go(); return { content: [ { type: 'text' as const, text: `${itemName} removed from inventory.` }, ], }; } catch { return { content: [ { type: 'text' as const, text: `${itemName} not found in inventory` }, ], }; } }
// If quantity is specified, fetch current quantity and update const item = await inventory.get({ playerName, itemName }).go();
if (!item.data) { return { content: [ { type: 'text' as const, text: `${itemName} not found in inventory` }, ], }; }
const newQuantity = item.data.quantity - quantity;
if (newQuantity <= 0) { await inventory.delete({ playerName, itemName }).go(); return { content: [ { type: 'text' as const, text: `${itemName} removed from inventory.` }, ], }; }
await inventory .put({ playerName, itemName, quantity: newQuantity, emoji: item.data.emoji, }) .go();
return { content: [ { type: 'text' as const, text: `Removed ${itemName} (x${quantity}) from inventory. ${newQuantity} remaining.`, }, ], }; }, );
return server;};import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';import { registerDivideTool } from './tools/divide.js';import { registerSampleGuidanceResource } from './resources/sample-guidance.js';import z from 'zod';import { createInventoryEntity } from '@dungeon-adventure/dungeon-db';
/** * Create the MCP Server */export const createServer = async () => { const server = new McpServer({ name: 'inventory-mcp-server', version: '1.0.0', });
registerDivideTool(server); registerSampleGuidanceResource(server); server.registerTool( 'list-inventory-items', { description: "List items in the player's inventory. Leave cursor blank unless you are requesting subsequent pages", inputSchema: { playerName: z.string(), cursor: z.string().optional(), }, }, async ({ playerName }) => { const inventory = await createInventoryEntity(); const results = await inventory.query .primary({ playerName, }) .go();
return { content: [{ type: 'text' as const, text: JSON.stringify(results) }], }; }, );
server.registerTool( 'add-to-inventory', { description: "Add an item to the player's inventory. Quantity defaults to 1 if omitted.", inputSchema: { playerName: z.string(), itemName: z.string(), emoji: z.string(), quantity: z.number().optional().default(1), }, }, async ({ playerName, itemName, emoji, quantity = 1 }) => { const inventory = await createInventoryEntity(); await inventory .put({ playerName, itemName, quantity, emoji, }) .go();
return { content: [ { type: 'text' as const, text: `Added ${itemName} (x${quantity}) to inventory`, }, ], }; }, );
server.registerTool( 'remove-from-inventory', { description: "Remove an item from the player's inventory. If quantity is omitted, all items are removed.", inputSchema: { playerName: z.string(), itemName: z.string(), quantity: z.number().optional(), }, }, async ({ playerName, itemName, quantity }) => { const inventory = await createInventoryEntity();
// If quantity is omitted, remove the entire item if (quantity === undefined) { try { await inventory.delete({ playerName, itemName }).go(); return { content: [ { type: 'text' as const, text: `${itemName} removed from inventory.` }, ], }; } catch { return { content: [ { type: 'text' as const, text: `${itemName} not found in inventory` }, ], }; } }
// If quantity is specified, fetch current quantity and update const item = await inventory.get({ playerName, itemName }).go();
if (!item.data) { return { content: [ { type: 'text' as const, text: `${itemName} not found in inventory` }, ], }; }
const newQuantity = item.data.quantity - quantity;
if (newQuantity <= 0) { await inventory.delete({ playerName, itemName }).go(); return { content: [ { type: 'text' as const, text: `${itemName} removed from inventory.` }, ], }; }
await inventory .put({ playerName, itemName, quantity: newQuantity, emoji: item.data.emoji, }) .go();
return { content: [ { type: 'text' as const, text: `Removed ${itemName} (x${quantity}) from inventory. ${newQuantity} remaining.`, }, ], }; }, );
return server;};Au fur et à mesure que le nombre d’outils augmente, vous pouvez les refactoriser dans des fichiers séparés si vous le souhaitez.
Supprimez les répertoires tools et resources dans packages/inventory/src/mcp-server car ils ne seront pas utilisés.
Tâche 3 : Mettre à jour l’infrastructure
Section intitulée « Tâche 3 : Mettre à jour l’infrastructure »Exposer le bucket de session
Section intitulée « Exposer le bucket de session »Le construct Story Agent provisionne déjà et écrit dans son propre bucket de session en interne, mais ne l’expose pas — donc rien en dehors de l’agent ne peut se voir accorder l’accès pour le lire pour le moment. Puisque queryActions a besoin de relire l’historique de conversation, pour l’illustration et la simplicité, nous allons exposer son bucket de session interne en tant que propriété publique sur common/constructs/src/app/agents/story-agent/story-agent.ts :
import { Fn, Lazy, Names, RemovalPolicy, Stack } from 'aws-cdk-lib';import { Platform } from 'aws-cdk-lib/aws-ecr-assets';import { Connections, IConnectable } from 'aws-cdk-lib/aws-ec2';import { BlockPublicAccess, Bucket, BucketEncryption, IBucket,} from 'aws-cdk-lib/aws-s3';import { Key } from 'aws-cdk-lib/aws-kms';import { CfnDelivery, CfnDeliveryDestination, CfnDeliverySource, LogGroup, RetentionDays,} from 'aws-cdk-lib/aws-logs';import { Construct } from 'constructs';import * as path from 'path';import * as url from 'url';import { AgentRuntimeArtifact, ProtocolType, Runtime, RuntimeProps, RuntimeAuthorizerConfiguration,} from 'aws-cdk-lib/aws-bedrockagentcore';import { PolicyStatement, Effect, ServicePrincipal, IGrantable, IPrincipal,} from 'aws-cdk-lib/aws-iam';import { IUserPool, IUserPoolClient } from 'aws-cdk-lib/aws-cognito';import { suppressRules } from '../../../core/checkov.js';import { RuntimeConfig } from '../../../core/runtime-config.js';import { findWorkspaceRoot } from '../../../core/workspace.js';
export type StoryAgentProps = Omit< RuntimeProps, | 'runtimeName' | 'protocolConfiguration' | 'agentRuntimeArtifact' | 'authorizerConfiguration'> & { /** * Identity details for Cognito Authentication */ identity: { userPool: IUserPool; userPoolClient: IUserPoolClient; }; /** * Removal policy for the session bucket holding the agent's conversation * history. Defaults to retaining it so a stack `destroy` doesn't silently * delete session data — set to `RemovalPolicy.DESTROY` for sandbox/CI teardown. * * @default RemovalPolicy.RETAIN */ readonly sessionBucketRemovalPolicy?: RemovalPolicy;};
export class StoryAgent extends Construct implements IGrantable, IConnectable { public readonly dockerImage: AgentRuntimeArtifact; public readonly agentCoreRuntime: Runtime; /** The S3 bucket backing this agent's session storage — exposed so other constructs (e.g. the Game API) can be granted access to read conversation history back. */ public readonly sessionBucket: IBucket; /** Default Gateway target name for this agent. */ public readonly agentName = 'story-agent'; /** Inbound auth — a fronting Gateway uses this to pick its outbound credential. */ public readonly auth = 'cognito';
constructor(scope: Construct, id: string, props: StoryAgentProps) { super(scope, id);
const rc = RuntimeConfig.ensure(this);
// Resolve the bundle output directory containing the Dockerfile and built artifacts const bundleDir = path.join( findWorkspaceRoot(url.fileURLToPath(new URL(import.meta.url))), 'dist/packages/story/docker/story-agent', );
this.dockerImage = AgentRuntimeArtifact.fromAsset(bundleDir, { platform: Platform.LINUX_ARM64, });
const { identity, sessionBucketRemovalPolicy = RemovalPolicy.RETAIN, ...restProps } = props ?? {};
const sessionKey = new Key(this, 'SessionKey', { enableKeyRotation: true, });
// Allow CloudWatch Logs to use the session key for server access log delivery. const stack = Stack.of(this); sessionKey.addToResourcePolicy( new PolicyStatement({ effect: Effect.ALLOW, principals: [ new ServicePrincipal(`logs.${stack.region}.amazonaws.com`), ], actions: [ 'kms:Encrypt', 'kms:Decrypt', 'kms:ReEncrypt*', 'kms:GenerateDataKey*', 'kms:DescribeKey', ], resources: ['*'], conditions: { ArnLike: { 'kms:EncryptionContext:aws:logs:arn': `arn:aws:logs:${stack.region}:${stack.account}:log-group:*`, }, }, }), );
const sessionAccessLogs = new LogGroup(this, 'SessionAccessLogs', { retention: RetentionDays.ONE_YEAR, encryptionKey: sessionKey, removalPolicy: RemovalPolicy.DESTROY, });
const sessionBucket = new Bucket(this, 'SessionBucket', { enforceSSL: true, removalPolicy: sessionBucketRemovalPolicy, encryption: BucketEncryption.KMS, encryptionKey: sessionKey, blockPublicAccess: BlockPublicAccess.BLOCK_ALL, }); this.sessionBucket = sessionBucket; suppressRules( sessionBucket, ['CKV_AWS_21'], 'Session data does not need versioning enabled', ); suppressRules( sessionBucket, ['CKV2_AWS_61'], 'Lifecycle configuration not required for session data', ); suppressRules( sessionBucket, ['CKV_AWS_144'], 'Cross-region replication not required for session data', ); suppressRules( sessionBucket, ['CKV2_AWS_62'], 'Event notifications not required for session data', ); suppressRules( sessionBucket, ['CKV_AWS_18'], 'Server access logs are delivered to CloudWatch Logs', );
const sessionAccessLogsSource: CfnDeliverySource = new CfnDeliverySource( this, 'SessionAccessLogsSource', { name: Lazy.string({ produce: () => Names.uniqueResourceName(sessionAccessLogsSource, { maxLength: 60, }), }), logType: 'S3_SERVER_ACCESS_LOGS', resourceArn: sessionBucket.bucketArn, }, ); const sessionBucketPolicy = sessionBucket.policy; if (sessionBucketPolicy) { sessionAccessLogsSource.node.addDependency(sessionBucketPolicy); } const sessionAccessLogsDestination: CfnDeliveryDestination = new CfnDeliveryDestination(this, 'SessionAccessLogsDestination', { name: Lazy.string({ produce: () => Names.uniqueResourceName(sessionAccessLogsDestination, { maxLength: 60, }), }), destinationResourceArn: sessionAccessLogs.logGroupArn, }); const sessionAccessLogsDelivery = new CfnDelivery( this, 'SessionAccessLogsDelivery', { deliverySourceName: sessionAccessLogsSource.name, deliveryDestinationArn: sessionAccessLogsDestination.attrArn, }, ); sessionAccessLogsDelivery.addDependency(sessionAccessLogsSource);
this.agentCoreRuntime = new Runtime(this, 'StoryAgent', { runtimeName: Lazy.string({ produce: () => Names.uniqueResourceName(this.agentCoreRuntime, { maxLength: 40 }), }), protocolConfiguration: ProtocolType.HTTP, agentRuntimeArtifact: this.dockerImage, authorizerConfiguration: RuntimeAuthorizerConfiguration.usingCognito( identity.userPool, [identity.userPoolClient], ), // Receive the caller's Authorization header (validated by the authorizer). requestHeaderConfiguration: { allowlistedHeaders: ['Authorization'], }, ...restProps, environmentVariables: { RUNTIME_CONFIG_APP_ID: rc.appConfigApplicationId, ...restProps?.environmentVariables, }, });
// Grant access for the agent to invoke bedrock models this.agentCoreRuntime.addToRolePolicy( new PolicyStatement({ actions: [ 'bedrock:InvokeModel', 'bedrock:InvokeModelWithResponseStream', ], resources: [ 'arn:aws:bedrock:*:*:foundation-model/*', 'arn:aws:bedrock:*:*:inference-profile/*', ], }), );
sessionBucket.grantReadWrite(this.agentCoreRuntime);
rc.grantReadAppConfig(this.agentCoreRuntime);
rc.set('agentcore', 'agentRuntimes', { ...rc.get('agentcore').agentRuntimes, StoryAgent: { arn: this.agentCoreRuntime.agentRuntimeArn, session: { bucketName: sessionBucket.bucketName, }, }, });
rc.set('connection', 'agentRuntimes', { ...rc.get('connection').agentRuntimes, StoryAgent: this.agentCoreRuntime.agentRuntimeArn, }); }
/** * The principal to grant permissions to. */ public get grantPrincipal(): IPrincipal { return this.agentCoreRuntime.grantPrincipal; }
/** * Network connections for this agent runtime. */ public get connections(): Connections { return this.agentCoreRuntime.connections; }
/** * The HTTPS invocation URL of the runtime. */ public get invocationUrl(): string { // The URL must URL-encode the runtime ARN (':' -> '%3A', '/' -> '%2F'). // The ARN is a CDK token, so encode at deploy time via Fn.join/Fn.split. const encodedArn = Fn.join( '%2F', Fn.split( '/', Fn.join('%3A', Fn.split(':', this.agentCoreRuntime.agentRuntimeArn)), ), ); return `https://bedrock-agentcore.${Stack.of(this).region}.amazonaws.com/runtimes/${encodedArn}/invocations?qualifier=DEFAULT`; }}Câbler la stack
Section intitulée « Câbler la stack »Le construct DungeonDb généré par ts#dynamodb provisionne déjà notre table, nous devons donc simplement l’instancier dans notre stack et accorder à l’API Game et au serveur MCP Inventory les permissions dont ils ont besoin. Mettez à jour packages/infra/src/stacks/application-stack.ts comme suit :
import { DungeonDb, GameApi, GameUI, InventoryMcpServer, StoryAgent, UserIdentity,} from '@dungeon-adventure/common-constructs';import { Stack, StackProps, CfnOutput, RemovalPolicy } from 'aws-cdk-lib';import { Construct } from 'constructs';
export class ApplicationStack extends Stack { constructor(scope: Construct, id: string, props?: StackProps) { super(scope, id, props);
const userIdentity = new UserIdentity(this, 'UserIdentity');
// Sandbox-friendly: allow the table to be deleted with the stack. const dungeonDb = new DungeonDb(this, 'DungeonDb', { deletionProtection: false, removalPolicy: RemovalPolicy.DESTROY, });
const gameApi = new GameApi(this, 'GameApi', { integrations: GameApi.defaultIntegrations(this).build(), });
dungeonDb.grantReadData(gameApi.integrations['games.query'].handler); dungeonDb.grantReadData(gameApi.integrations['inventory.query'].handler); dungeonDb.grantReadWriteData(gameApi.integrations['games.save'].handler);
const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer'); dungeonDb.grantReadWriteData(mcpServer.agentCoreRuntime);
// Use Cognito for user authentication with the agent const storyAgent = new StoryAgent(this, 'StoryAgent', { identity: userIdentity, }); // The agent's own session bucket already persists conversation history via // S3SessionManager; grant the Game API read access so it can replay it. storyAgent.sessionBucket.grantRead( gameApi.integrations['actions.query'].handler, );
new CfnOutput(this, 'StoryAgentArn', { value: storyAgent.agentCoreRuntime.agentRuntimeArn, }); new CfnOutput(this, 'InventoryMcpArn', { value: mcpServer.agentCoreRuntime.agentRuntimeArn, });
// Grant the agent permissions to invoke our mcp server mcpServer.grantInvokeAccess(storyAgent);
// Grant the authenticated role access to invoke the api gameApi.grantInvokeAccess(userIdentity.identityPool.authenticatedRole);
new GameUI(this, 'GameUI'); }}import { DungeonDb, GameApi, GameUI, InventoryMcpServer, StoryAgent, UserIdentity,} from '@dungeon-adventure/common-constructs';import { Stack, StackProps, CfnOutput } from 'aws-cdk-lib';import { Stack, StackProps, CfnOutput, RemovalPolicy } from 'aws-cdk-lib';import { Construct } from 'constructs';
export class ApplicationStack extends Stack { constructor(scope: Construct, id: string, props?: StackProps) { super(scope, id, props);
const userIdentity = new UserIdentity(this, 'UserIdentity');
// Sandbox-friendly: allow the table to be deleted with the stack. const dungeonDb = new DungeonDb(this, 'DungeonDb', { deletionProtection: false, removalPolicy: RemovalPolicy.DESTROY, });
const gameApi = new GameApi(this, 'GameApi', { integrations: GameApi.defaultIntegrations(this).build(), });
dungeonDb.grantReadData(gameApi.integrations['games.query'].handler); dungeonDb.grantReadData(gameApi.integrations['inventory.query'].handler); dungeonDb.grantReadWriteData(gameApi.integrations['games.save'].handler);
const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer'); dungeonDb.grantReadWriteData(mcpServer.agentCoreRuntime);
// Use Cognito for user authentication with the agent const storyAgent = new StoryAgent(this, 'StoryAgent', { identity: userIdentity, }); // The agent's own session bucket already persists conversation history via // S3SessionManager; grant the Game API read access so it can replay it. storyAgent.sessionBucket.grantRead( gameApi.integrations['actions.query'].handler, );
new CfnOutput(this, 'StoryAgentArn', { value: storyAgent.agentCoreRuntime.agentRuntimeArn, }); new CfnOutput(this, 'InventoryMcpArn', { value: mcpServer.agentCoreRuntime.agentRuntimeArn, });
// Grant the agent permissions to invoke our mcp server mcpServer.grantInvokeAccess(storyAgent);
// Grant the authenticated role access to invoke the api gameApi.grantInvokeAccess(userIdentity.identityPool.authenticatedRole);
new GameUI(this, 'GameUI'); }}Tâche 4 : Tester l’API Game localement
Section intitulée « Tâche 4 : Tester l’API Game localement »Il n’est pas nécessaire de déployer sur AWS pour essayer notre API — la cible dev exécute l’API Game contre DynamoDB Local. Parce que nous avons connecté l’API Game au projet DungeonDb dans le Module 1, cette cible démarre également DynamoDB Local automatiquement.
Tout d’abord, corrigez les problèmes de lint :
pnpm lintyarn lintnpm run lintbun lintEnsuite, construisez la base de code :
pnpm buildyarn buildnpm run buildbun buildDémarrer le serveur local
Section intitulée « Démarrer le serveur local »Démarrez l’API Game localement avec la cible dev, qui démarre également DynamoDB Local :
pnpm nx dev game-apiyarn nx dev game-apinpx nx dev game-apibunx nx dev game-apiTester l’API
Section intitulée « Tester l’API »Une fois votre serveur opérationnel, interrogez la liste (vide) des parties :
curl -X GET 'http://localhost:2022/games.query?input=%7B%7D'Vous verrez une liste vide :
{"result":{"data":{"items":[],"cursor":null}}}Maintenant, sauvegardez une partie :
curl -X POST 'http://localhost:2022/games.save' \ -H 'Content-Type: application/json' \ -d '{"playerName":"Alice","genre":"zombie"}'La sauvegarde retourne la partie persistée (avec l’horodatage lastUpdated que l’entité définit pour vous) :
{"result":{"data":{"playerName":"Alice","genre":"zombie","lastUpdated":"..."}}}Interrogez à nouveau pour confirmer qu’elle est persistée dans DynamoDB Local :
curl -X GET 'http://localhost:2022/games.query?input=%7B%7D'Cette réponse inclut maintenant la partie sauvegardée :
{"result":{"data":{"items":[{"playerName":"Alice","genre":"zombie","lastUpdated":"..."}],"cursor":null}}}Vous pouvez arrêter le serveur local (Ctrl+C) une fois que vous avez terminé.
Tâche 5 : Tester le serveur MCP Inventory localement
Section intitulée « Tâche 5 : Tester le serveur MCP Inventory localement »Nous pouvons essayer les outils du serveur MCP avec le MCP Inspector en utilisant la cible générée mcp-server-inspect :
pnpm nx mcp-server-inspect inventoryyarn nx mcp-server-inspect inventorynpx nx mcp-server-inspect inventorybunx nx mcp-server-inspect inventoryCela sert le serveur MCP localement (en démarrant également DynamoDB Local) et lance le MCP Inspector à http://localhost:6274 préconfiguré pour s’y connecter. Cliquez sur Connect, passez à l’onglet Tools, cliquez sur List Tools, et essayez add-to-inventory (par exemple playerName: Alice, itemName: Rusty Sword, emoji: ⚔️) suivi de list-inventory-items pour le voir persisté dans DynamoDB Local. Arrêtez le serveur (Ctrl+C) lorsque vous avez terminé.
Félicitations, vous avez construit et testé votre première API tRPC et serveur MCP contre une table DynamoDB locale ! 🎉🎉🎉