Petstore MCP Server
A read-only MCP server that exposes Swagger Petstore v2 GET endpoints as tools for searching available pets, fetching pet details, and checking inventory.
README
Theorvane Petstore MCP Example
A single runnable example showing a truthful end-to-end path from the public Swagger Petstore v2 demo API to a TypeChain @Agent() that uses an actual local MCP HTTP session.
What this proves
Swagger Petstore v2 GET API
→ injected PetstoreClient
→ TypeMCP @McpServer() / @McpTool()
→ TypeMCP Streamable HTTP handler
→ local 127.0.0.1 ephemeral-port MCP runtime
→ official MCP SDK client session
→ TypeChain @Agent() + @Tool() MCP-client façade
→ TypeChain buildAgent() / LangChain agent loop
The fixture run proves the MCP SDK client performs protocol initialization, tools/list, and tools/call over loopback Streamable HTTP. It also proves a LangChain FakeToolCallingModel selects search_available_pets, and the TypeChain @Agent() façade sends that call through the MCP client rather than calling the REST client or TypeMCP server directly.
Prerequisites
- Node.js 20 or newer
- npm 10 or newer
npm ci
npm run check
Run the deterministic MCP agent example
npm run example:petstore:mcp-agent:fixture
It starts an in-process Node HTTP server bound only to 127.0.0.1 on an ephemeral port, connects the official MCP SDK StreamableHTTPClientTransport, discovers the tools, runs the agent loop, and shuts down the MCP client session and HTTP server in finally blocks.
Expected result contains fixture data:
{
"discoveredTools": [
"search_available_pets",
"get_pet",
"get_petstore_inventory"
],
"tool": "search_available_pets",
"result": [
{ "id": 1, "name": "Milo", "status": "available" },
{ "id": 2, "name": "Nori", "status": "available" }
]
}
For the narrower protocol-only smoke run (loopback URL, 404 route boundary, tools/list, and tools/call), use:
npm run example:petstore:mcp:fixture
Optional public REST smoke run
npm run example:petstore:live
This calls the mutable public Swagger Petstore demo API. Its data and uptime are outside this repository's control, so it is not used by tests or CI. The command is a GET-only REST smoke run; it does not demonstrate MCP client connectivity or a model-backed agent.
Read-only Petstore contract
PetstoreClient has a fixed base URL, https://petstore.swagger.io/v2, and only sends GET requests. The TypeMCP server exposes exactly three tools:
| MCP tool | REST operation |
|---|---|
search_available_pets |
GET /pet/findByStatus?status=available |
get_pet |
GET /pet/{petId} |
get_petstore_inventory |
GET /store/inventory |
The example has no create, update, delete, API-key, credential, environment-configured API host, or public listener path.
Application-owned model runtime
The fixture uses FakeToolCallingModel, not a live provider. An application that wants a real model must install/configure that model itself, then pass it together with a connected MCP client to the agent builder:
import { buildPetstoreMcpAgent } from "./examples/typechain-petstore-mcp-agent.js";
// The consuming application chooses, authenticates, and authorizes this model.
declare const applicationModel: Parameters<
typeof buildPetstoreMcpAgent
>[0]["model"];
// The application owns the lifecycle of this client connection.
declare const connectedMcpClient: Parameters<
typeof buildPetstoreMcpAgent
>[0]["client"];
const agent = buildPetstoreMcpAgent({
model: applicationModel,
client: connectedMcpClient,
});
This repository deliberately does not select a provider/model, install provider SDKs, read credentials or process.env, run a live LLM command, or implement authorization/retry/audit/redaction policy.
Example-only runtime boundary
The loopback runtime is a deterministic integration example, not a production deployment recipe. It intentionally does not provide public hosting, authentication, authorization, durable sessions, a reverse proxy, observability, deployment configuration, or persistent MCP lifecycle management. A production application must own those decisions.
Development
npm run lint
npm run build
npm test
npm run audit:prod
npm run check
Packages
@theorvane/type-chain0.1.1@theorvane/type-mcp0.2.2or later within the0.2.xrange
License
MIT © Theorvane
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。