@modelcontextprotocol/[email protected] 破坏性变更：HTTP
@modelcontextprotocol/[email protected]
推荐理由
MCP Hono 适配者必读：v2.0.2 改变了连接模型，复用单例会导致并发请求静默失败。请立即检查代码，确保在 handler 内按需实例化 McpServer 和 Transport，避免线上出现 500 错误。
Patch Changes
补丁更改
- #2918 84804c2 Thanks @claude! - A Server or McpServer now serves one connection at a time, and a Streamable HTTP server transport without sessions (sessionIdGenerator: undefined) serves one request. An app that uses one server object, or one stateless transport, for every HTTP request fails on the second request after this upgrade. Build the server and the transport per request instead.
- What keeps working without a change:
- createMcpHandler(buildServer) and serveStdio(buildServer), where buildServer returns a new server on every call.
- A handler that builds a new server and a new stateless transport for each request.
- One server and one transport per session (a transport with a sessionIdGenerator).
- Connecting a server again after close().
- Client.
- What fails now, how it shows, and what to change:
- One server object with a new stateless transport per request (const server = new McpServer(...) outside the handler, await server.connect(transport) inside it): the second HTTP request the process receives fails, and so does every later one. connect() rejects with an SdkError of code ALREADY_CONNECTED. If the handler closes the transport when the response ends, requests that arrive one after the other still work and a request that overlaps another one fails. Change: move new McpServer(...) and its registrations into the handler.
- One stateless transport for every request (a transport built once with sessionIdGenerator: undefined): the second HTTP request fails. WebStandardStreamableHTTPServerTransport.handleRequest() rejects with Stateless transport cannot be reused across requests. Create a new transport per request., and NodeStreamableHTTPServerTransport.handleRequest() answers 500. Change: build the server and the transport inside the handler and connect them there.
- createMcpHandler(() => server) with a server built once: a request that arrives after the previous response has been read to its end still works. A request that arrives while another one is being served is answered 500 with the JSON-RPC error -32603 (Internal server error); the reason is reported only through the onerror option. Change: pass a function that builds the server, as in createMcpHandler(buildServer).
- One server object for every session: the initialize request of the second session fails with ALREADY_CONNECTED. Change: build a server per session.
- What the caller sees when connect() or handleRequest() rejects depends on the host. Express 5, Fastify and Hono answer 500. A plain node:http listener without its own error handling gets an unhandled rejection, which ends the process.
- The README examples of @modelcontextprotocol/express, @modelcontextprotocol/fastify, @modelcontextprotocol/hono and @modelcontextprotocol/node, and the handler examples in the JSDoc of WebStandardStreamableHTTPServerTransport and NodeStreamableHTTPServerTransport, now build a server and a transport per request.
- #2908 633dd3e Thanks @claude! - The license field of the package manifests is now Apache-2.0; the LICENSE file shipped in each package carries the full terms, including the MIT text for earlier contributions. No code change.
- Updated dependencies [40f8f4e, 6d8dbc6, 5238fba, 2fc49ea, 4d94e7b, 84804c2, e55f9ac, 633dd3e, 2237555]:
- @modelcontextprotocol/[email protected]
- #2918 84804c2 感谢 @claude！- Server 或 McpServer 现在一次仅服务一个连接，且没有会话（sessionIdGenerator: undefined）的 Streamable HTTP 服务器传输层一次仅处理一个请求。如果应用对每个 HTTP 请求使用一个服务器对象或一个无状态传输层，则在本次升级后的第二个请求会失败。改为为每个请求构建服务器和传输层。
- 无需更改即可继续正常工作的内容：
- createMcpHandler(buildServer) 和 serveStdio(buildServer)，其中 buildServer 每次调用都返回一个新的服务器。
- 为每个请求构建新服务器和新无状态传输层的处理器。
- 每个会话一个服务器和一个传输层（带有 sessionIdGenerator 的传输层）。
- 在 close() 之后重新连接服务器。
- 客户端。
- 现在哪些功能会失败、表现如何以及需要做出哪些更改：
- 每个请求使用一个新无状态传输层的一个服务器对象（const server = new McpServer(...) 在处理器外部定义，await server.connect(transport) 在其内部执行）：进程接收到的第二个 HTTP 请求会失败，后续所有请求也会失败。connect() 会抛出代码为 ALREADY_CONNECTED 的 SdkError。如果处理器在响应结束时关闭传输层，连续到达的请求仍能正常工作，但与其他请求重叠的请求会失败。更改方法：将 new McpServer(...) 及其注册逻辑移入处理器中。
- 每个请求使用一个无状态传输层（通过 sessionIdGenerator: undefined 一次性构建的传输层）：第二个 HTTP 请求会失败。WebStandardStreamableHTTPServerTransport.handleRequest() 会拒绝并提示“Stateless transport cannot be reused across requests. Create a new transport per request.”，而 NodeStreamableHTTPServerTransport.handleRequest() 则返回 500 错误。更改方法：在处理器内部构建服务器和传输层，并在其中进行连接。
- 使用一次性构建的服务器的 createMcpHandler(() => server)：在当前响应读取到末尾后到达的请求仍可正常工作。而在另一个请求正在被服务时到达的请求会返回 500 错误及 JSON-RPC 错误 -32603（内部服务器错误）；该原因仅通过 onerror 选项报告。更改方法：传递一个用于构建服务器的函数，如 createMcpHandler(buildServer)。
- 每个会话使用一个服务器对象：第二个会话的 initialize 请求会因 ALREADY_CONNECTED 而失败。更改方法：为每个会话构建一个服务器。
- 当 connect() 或 handleRequest() 被拒绝时，调用者看到的内容取决于主机。Express 5、Fastify 和 Hono 返回 500。没有自带错误处理的普通 node:http 监听器会收到未处理的拒绝（unhandled rejection），从而导致进程终止。
- @modelcontextprotocol/express、@modelcontextprotocol/fastify、@modelcontextprotocol/hono 和 @modelcontextprotocol/node 的 README 示例，以及 WebStandardStreamableHTTPServerTransport 和 NodeStreamableHTTPServerTransport JSDoc 中的处理程序示例，现在改为每个请求构建一个服务器和一个传输层。
- #2908 633dd3e 感谢 @claude！- 包清单中的许可证字段现已更新为 Apache-2.0；每个包附带的 LICENSE 文件包含完整条款，包括针对早期贡献的 MIT 文本。无代码变更。
- 已更新依赖项 [40f8f4e, 6d8dbc6, 5238fba, 2fc49ea, 4d94e7b, 84804c2, e55f9ac, 633dd3e, 2237555]：
- @modelcontextprotocol/[email protected]
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力