Implement the Game API and Inventory MCP server

Task 1: Implement the Game API

We will implement the following APIs in this section:

1. saveGame - create or update a game.
2. queryGames - return a paginated list of previously saved games.
3. queryInventory - return a paginated list of items in a player’s inventory.
4. queryActions - return the conversation history for a given game.

Where each piece of state lives

• games and inventory are in DynamoDB (via ElectroDB) — the Game API lambdas and the Inventory MCP server read/write them.
• actions (chat transcript) is in S3 — the Story Agent’s S3SessionManager writes one JSON blob per turn, and queryActions in the Game API reads them back so the UI can replay history on page reload. There’s no saveAction procedure; the agent is the only writer.

API schema

To define our API inputs and outputs, let’s create our schema using Zod within the packages/game-api/src/schema/index.ts file as follows:

+

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(),
  });
};

Delete the packages/game-api/src/schema/echo.ts file as we will not be using it in this project.

Automatic Type Inference

For each of the schemas we define in Zod, we also export an interface using the z.TypeOf syntax. This converts our Zod definition into a Typescript interface without having to duplicate effort.

Entity modelling

This is the ER diagram for our application.

We will implement our database in DynamoDB, and will use the ElectroDB DynamoDB client library to simplify things. The Game API’s queryActions also needs the S3 client to read conversation turns the agent has written. Install them all with:

pnpm

pnpm add -w electrodb@3.7.5 @aws-sdk/client-dynamodb@3.1053.0 @aws-sdk/client-s3@3.1053.0

yarn

yarn add electrodb@3.7.5 @aws-sdk/client-dynamodb@3.1053.0 @aws-sdk/client-s3@3.1053.0

npm

npm install --legacy-peer-deps electrodb@3.7.5 @aws-sdk/client-dynamodb@3.1053.0 @aws-sdk/client-s3@3.1053.0

bun

bun install electrodb@3.7.5 @aws-sdk/client-dynamodb@3.1053.0 @aws-sdk/client-s3@3.1053.0

Root Dependencies

All dependencies are added to the root package.json as the @aws/nx-plugin follows the single version policy principle. For more information, refer to the ts#project guide.

To define our ElectroDB entities from the ER Diagram, let’s create the packages/game-api/src/entities/index.ts file:

import { Entity } from 'electrodb';
import { DynamoDBClient } from '@aws-sdk/client-dynamodb';
import { getAppConfig } from '@aws-lambda-powertools/parameters/appconfig';

/**
 * Resolves the DynamoDB table name from runtime config (AppConfig).
 */
const resolveTableName = async (): Promise<string> => {
  const tablesConfig = await getAppConfig('tables', {
    application: process.env.RUNTIME_CONFIG_APP_ID!,
    environment: 'default',
    transform: 'json',
  });

  const tableName = (tablesConfig as Record<string, any>).ElectroDbTable?.tableName;
  if (!tableName) {
    throw new Error(
      'Could not resolve table name from runtime config',
    );
  }
  return tableName;
};

export const createGameEntity = async (client: DynamoDBClient = new DynamoDBClient()) =>
  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, table: await resolveTableName() },
  );

export const createInventoryEntity = async (client: DynamoDBClient = new DynamoDBClient()) =>
  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, table: await resolveTableName() },
  );

ElectroDB allows us to not only define our types, but can also provide defaults for certain values like timestamps. In addition, ElectroDB follows single-table design which is the best practice when using DynamoDB.

ElectroDB Collections

Whilst ElectroDB does support collections, we have chosen not to use them in this tutorial for simplicity.

To prepare for the MCP server to interact with the inventory, let’s ensure we export the inventory entity in packages/game-api/src/index.ts:

packages/game-api/src/index.ts

export type { AppRouter } from './router.js';
export { appRouter } from './router.js';
export type { Context } from './init.js';
export * from './client/index.js';
export * from './schema/index.js';
export * from './entities/index.js';

Package Structure

The package structure would be better if we refactored entities into their own shared project so that the MCP server does not need to depend on the API.

Defining our procedures

To implement the API methods, make the following changes within packages/game-api/src/procedures:

games.ts

import { createGameEntity } from '../entities/index.js';
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;
  });

inventory.ts

import {
  ItemSchema,
  QueryInputSchema,
  createPaginatedQueryOutput,
} from '../schema/index.js';
import { publicProcedure } from '../init.js';
import { z } from 'zod';
import { createInventoryEntity } from '../entities/index.js';

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,
    };
  });

actions.ts

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 buckets = await getAppConfig('buckets', {
    application: process.env.RUNTIME_CONFIG_APP_ID!,
    environment: 'default',
    transform: 'json',
  });
  const bucket = (buckets as Record<string, any>).StorySessions?.bucketName;
  if (!bucket)
    throw new Error('StorySessions bucket not found in runtime config');
  return bucket;
};

const s3 = new S3Client();
const LOCAL_SESSION_STORAGE_DIR = '/tmp/strands-sessions';

// 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.SERVE_LOCAL === 'true'
        ? await readLocalActions(input.sessionId)
        : await readS3Actions(input.sessionId);
    return { items: actions };
  });

Delete the echo.ts file (from packages/game-api/src/procedures) as we will not be using it in this project.

Router setup

After we define our procedures, to wire them into our API, update the following file:

packages/game-api/src/router.ts

+

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;

Task 2: Create an Inventory MCP server

Let us create an MCP server which will allow our agent to manage items in a player’s inventory.

We’ll define the following tools for our agent:

• list-inventory-items for retrieving the player’s current inventory items
• add-to-inventory for adding items to the player’s inventory
• remove-from-inventory for removing items from the player’s inventory

To save time, we will define all the tools inline:

packages/inventory/src/mcp-server/server.ts

+

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
import z from 'zod';
import { createInventoryEntity } from ':dungeon-adventure/game-api';

/**
 * 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/game-api';

/**
 * 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;
};

As the number of tools grow, you can refactor them out into separate files if you like.

Delete the tools and resources directories in packages/inventory/src/mcp-server as these will not be used.

Task 3: Update the infrastructure

The final step is to update our infrastructure to create the DynamoDB table and grant permissions to perform operations from the Game API. To do so, update the packages/infra/src as follows:

constructs/electrodb-table.ts

import { CfnOutput } from 'aws-cdk-lib';
import {
  AttributeType,
  BillingMode,
  ProjectionType,
  Table,
  TableProps,
} from 'aws-cdk-lib/aws-dynamodb';
import { Construct } from 'constructs';
import { suppressRules } from ':dungeon-adventure/common-constructs';

export type ElectrodbDynamoTableProps = Omit<
  TableProps,
  'partitionKey' | 'sortKey' | 'billingMode'
>;

export class ElectrodbDynamoTable extends Table {
  constructor(scope: Construct, id: string, props?: ElectrodbDynamoTableProps) {
    super(scope, id, {
      partitionKey: {
        name: 'pk',
        type: AttributeType.STRING,
      },
      sortKey: {
        name: 'sk',
        type: AttributeType.STRING,
      },
      billingMode: BillingMode.PAY_PER_REQUEST,
      ...props,
    });

    this.addGlobalSecondaryIndex({
      indexName: 'gsi1pk-gsi1sk-index',
      partitionKey: {
        name: 'gsi1pk',
        type: AttributeType.STRING,
      },
      sortKey: {
        name: 'gsi1sk',
        type: AttributeType.STRING,
      },
      projectionType: ProjectionType.ALL,
    });

    // Suppress checkov rules that expect a KMS customer managed key and backup to be enabled
    suppressRules(this, ['CKV_AWS_119', 'CKV_AWS_28'], 'No need for custom encryption or backup');

    new CfnOutput(this, 'TableName', { value: this.tableName });
  }
}

stacks/application-stack.ts

+

import {
  GameApi,
  GameUI,
  InventoryMcpServer,
  RuntimeConfig,
  StoryAgent,
  UserIdentity,
  suppressRules,
} from ':dungeon-adventure/common-constructs';
import { Stack, StackProps, CfnOutput, RemovalPolicy } from 'aws-cdk-lib';
import {
  BlockPublicAccess,
  Bucket,
  BucketEncryption,
} from 'aws-cdk-lib/aws-s3';
import { Construct } from 'constructs';
import { ElectrodbDynamoTable } from '../constructs/electrodb-table.js';

export class ApplicationStack extends Stack {
  constructor(scope: Construct, id: string, props?: StackProps) {
    super(scope, id, props);

    const rc = RuntimeConfig.ensure(this);

    const userIdentity = new UserIdentity(this, 'UserIdentity');

    const electroDbTable = new ElectrodbDynamoTable(this, 'ElectroDbTable');

    // Register the table name in runtime config 'tables' namespace
    rc.set('tables', 'ElectroDbTable', {
      tableName: electroDbTable.tableName,
    });

    // S3 bucket for Strands conversation history. The Story Agent writes each
    // turn via ``S3SessionManager``; the Game API reads them back for replay.
    const storySessions = new Bucket(this, 'StorySessions', {
      encryption: BucketEncryption.S3_MANAGED,
      blockPublicAccess: BlockPublicAccess.BLOCK_ALL,
      enforceSSL: true,
      removalPolicy: RemovalPolicy.DESTROY,
      autoDeleteObjects: true,
    });
    suppressRules(
      storySessions,
      ['CKV_AWS_18', 'CKV_AWS_21'],
      'Access logging and object versioning are unnecessary for ephemeral chat transcripts',
    );
    rc.set('buckets', 'StorySessions', {
      bucketName: storySessions.bucketName,
    });

    const gameApi = new GameApi(this, 'GameApi', {
      integrations: GameApi.defaultIntegrations(this).build(),
    });

    electroDbTable.grantReadData(gameApi.integrations['games.query'].handler);
    electroDbTable.grantReadData(
      gameApi.integrations['inventory.query'].handler,
    );
    electroDbTable.grantReadWriteData(
      gameApi.integrations['games.save'].handler,
    );
    storySessions.grantRead(gameApi.integrations['actions.query'].handler);

    const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer');
    electroDbTable.grantReadWriteData(mcpServer.agentCoreRuntime);

    // Use Cognito for user authentication with the agent
    const storyAgent = new StoryAgent(this, 'StoryAgent', {
      identity: userIdentity,
    });
    storySessions.grantReadWrite(storyAgent);

    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 {
  GameApi,
  GameUI,
  InventoryMcpServer,
  RuntimeConfig,
  StoryAgent,
  UserIdentity,
  suppressRules,
} from ':dungeon-adventure/common-constructs';
import { Stack, StackProps, CfnOutput } from 'aws-cdk-lib';
import { Stack, StackProps, CfnOutput, RemovalPolicy } from 'aws-cdk-lib';
import {
  BlockPublicAccess,
  Bucket,
  BucketEncryption,
} from 'aws-cdk-lib/aws-s3';
import { Construct } from 'constructs';
import { ElectrodbDynamoTable } from '../constructs/electrodb-table.js';

export class ApplicationStack extends Stack {
  constructor(scope: Construct, id: string, props?: StackProps) {
    super(scope, id, props);

    const rc = RuntimeConfig.ensure(this);

    const userIdentity = new UserIdentity(this, 'UserIdentity');

    const electroDbTable = new ElectrodbDynamoTable(this, 'ElectroDbTable');

    // Register the table name in runtime config 'tables' namespace
    rc.set('tables', 'ElectroDbTable', {
      tableName: electroDbTable.tableName,
    });

    // S3 bucket for Strands conversation history. The Story Agent writes each
    // turn via ``S3SessionManager``; the Game API reads them back for replay.
    const storySessions = new Bucket(this, 'StorySessions', {
      encryption: BucketEncryption.S3_MANAGED,
      blockPublicAccess: BlockPublicAccess.BLOCK_ALL,
      enforceSSL: true,
      removalPolicy: RemovalPolicy.DESTROY,
      autoDeleteObjects: true,
    });
    suppressRules(
      storySessions,
      ['CKV_AWS_18', 'CKV_AWS_21'],
      'Access logging and object versioning are unnecessary for ephemeral chat transcripts',
    );
    rc.set('buckets', 'StorySessions', {
      bucketName: storySessions.bucketName,
    });

    const gameApi = new GameApi(this, 'GameApi', {
      integrations: GameApi.defaultIntegrations(this).build(),
    });

    electroDbTable.grantReadData(gameApi.integrations['games.query'].handler);
    electroDbTable.grantReadData(
      gameApi.integrations['inventory.query'].handler,
    );
    electroDbTable.grantReadWriteData(
      gameApi.integrations['games.save'].handler,
    );
    storySessions.grantRead(gameApi.integrations['actions.query'].handler);

    const mcpServer = new InventoryMcpServer(this, 'InventoryMcpServer');
    electroDbTable.grantReadWriteData(mcpServer.agentCoreRuntime);

    // Use Cognito for user authentication with the agent
    const storyAgent = new StoryAgent(this, 'StoryAgent', {
      identity: userIdentity,
    });
    storySessions.grantReadWrite(storyAgent);

    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');
  }
}

Isolated Procedures

Notice here that since each procedure is served by an individual lambda function, we can follow the principle of least privilege and assign only the required read/write permissions based on the procedure’s implementation.

Runtime Configuration

The DynamoDB table name is registered in Runtime Configuration under the tables namespace, stored in AWS AppConfig. Lambda functions and the MCP server retrieve it at runtime using Lambda Powertools, rather than needing it passed as an environment variable. A benefit of this approach is that as the number of tables or other infrastructure identifiers grows, you only need a single RUNTIME_CONFIG_APP_ID environment variable when running locally.

Task 4: Deployment and testing

First, fix any lint issues:

pnpm

pnpm lint

yarn

yarn lint

npm

npm run lint

bun

bun lint

Then build the codebase:

pnpm

pnpm build

yarn

yarn build

npm

npm run build

bun

bun build

Deploy your application

To deploy your application, run the following command:

pnpm

pnpm nx deploy infra "dungeon-adventure-infra-sandbox/*"

yarn

yarn nx deploy infra "dungeon-adventure-infra-sandbox/*"

npm

npx nx deploy infra "dungeon-adventure-infra-sandbox/*"

bun

bunx nx deploy infra "dungeon-adventure-infra-sandbox/*"

Bootstrap Required

To bootstrap your AWS Account first, run:

pnpm

pnpm nx bootstrap infra

yarn

yarn nx bootstrap infra

npm

npx nx bootstrap infra

bun

bunx nx bootstrap infra

Your first deployment will take around 8 minutes to complete. Subsequent deployments will take around 2 minutes.

Fast Iteration

If you’re iterating on Lambda function code changes, you can deploy with the --hotswap flag after building the codebase for a much shorter (2-3 second) deployment time.

pnpm

pnpm nx deploy infra "dungeon-adventure-infra-sandbox/*" --hotswap

yarn

yarn nx deploy infra "dungeon-adventure-infra-sandbox/*" --hotswap

npm

npx nx deploy infra "dungeon-adventure-infra-sandbox/*" --hotswap

bun

bunx nx deploy infra "dungeon-adventure-infra-sandbox/*" --hotswap

Once the deployment completes, you will see outputs similar to the following (some values have been redacted):

dungeon-adventure-infra-sandbox-Application
dungeon-adventure-infra-sandbox-Application: deploying... [2/2]

 ✅  dungeon-adventure-infra-sandbox-Application

✨  Deployment time: 354s

Outputs:
dungeon-adventure-infra-sandbox-Application.ElectroDbTableTableNameXXX = dungeon-adventure-infra-sandbox-Application-ElectroDbTableXXX-YYY
dungeon-adventure-infra-sandbox-Application.GameApiEndpointXXX = https://xxx.execute-api.region.amazonaws.com/prod/
dungeon-adventure-infra-sandbox-Application.GameUIDistributionDomainNameXXX = xxx.cloudfront.net
dungeon-adventure-infra-sandbox-Application.InventoryMcpArn = arn:aws:bedrock-agentcore:region:xxxxxxx:runtime/dungeonadventureventoryMcpServerXXXX-YYYY
dungeon-adventure-infra-sandbox-Application.RuntimeConfigApplicationId = xxxx
dungeon-adventure-infra-sandbox-Application.StoryAgentArn = arn:aws:bedrock-agentcore:region:xxxxxxx:runtime/dungeonadventurecationStoryAgentXXXX-YYYY
dungeon-adventure-infra-sandbox-Application.UserIdentityUserIdentityIdentityPoolIdXXX = region:xxx
dungeon-adventure-infra-sandbox-Application.UserIdentityUserIdentityUserPoolClientIdXXX = xxxxxxxxxx
dungeon-adventure-infra-sandbox-Application.UserIdentityUserIdentityUserPoolIdXXX = region_xxx

Test the API

You can test the API by either:

• Starting a local instance of the tRPC backend and invoke the APIs using curl.
• Calling the deployed API using sigv4 enabled curl

Local

To start your local game-api server, run the following command:

pnpm

RUNTIME_CONFIG_APP_ID=xxxx pnpm nx serve game-api

yarn

RUNTIME_CONFIG_APP_ID=xxxx yarn nx serve game-api

npm

RUNTIME_CONFIG_APP_ID=xxxx npx nx serve game-api

bun

RUNTIME_CONFIG_APP_ID=xxxx bunx nx serve game-api

Use CDK Output Values

Use the CDK deploy output value of dungeon-adventure-infra-sandbox-Application.RuntimeConfigApplicationId to replace the highlighted placeholder.

Once your server is up and running, you can call it by running the following command:

curl -X GET 'http://localhost:2022/games.query?input=%7B%7D'

Deployed

acurl ap-southeast-2 execute-api -X GET 'https://xxx.execute-api.ap-southeast-2.amazonaws.com/prod/games.query?input=%7B%7D'

Use CDK Output Values

Use the CDK deploy output value of dungeon-adventure-infra-sandbox-Application.GameApiGameApiEndpointXXX to replace the highlighted placeholder and set the region accordingly.

URL Encoding

The %7B%7D we pass to test the API is a URI encoded empty JSON object ({}).

If the command runs successfully, you will see a response as follows:

{"result":{"data":{"items":[],"cursor":null}}}

Congratulations, you have built and deployed your first API using tRPC! 🎉🎉🎉