modelcontextprotocol / modelcontextprotocol/python-sdk

MCPServer handlers should raise exceptions, not return error objects

未关闭
#2,153 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

enhancement v2
主要语言
Python
星标
24.3k
派生
4k
平均合并
1 天 1 小时
30 天内合并 PR
31

描述

Problem

The current error handling across the two server layers is inconsistent and confusing for users. As noted by Marcelo, the experience should be more like Starlette's raise HTTPException pattern.

Current behavior

MCPServer (high-level) tool handlers:

  • Raising any exception → caught by Tool.run(), re-wrapped as ToolError, then caught by _handle_call_tool()CallToolResult(isError=True) (a JSON-RPC success response)
  • Raising MCPError → re-raised past _handle_call_tool() → becomes a JSON-RPC error response
  • Returning CallToolResult(isError=True) directly → also works
  • Resource/prompt handlers have no try/except at the MCPServer layer — exceptions propagate to the low-level server

Low-level server handlers:

  • _handle_request() catches MCPError → sends its .error as a JSON-RPC error
  • Any other ExceptionErrorData(code=0, message=str(err)) → JSON-RPC error with non-standard code

Users need to understand the difference between ToolError, MCPError, CallToolResult(isError=True), and plain exceptions — each produces different behavior depending on which layer catches it.

Desired behavior
  1. MCPServer users should raise exceptions to signal errors — the framework converts them to the appropriate protocol response. No need to construct and return error result objects.
  2. Low-level server users should return ErrorData explicitly when they want to control the JSON-RPC error response, since they operate at the protocol level.
  3. Unhandled exceptions at either layer should be caught gracefully by the framework and returned as a well-formed JSON-RPC error, without leaking internal details to the client.
Related issues
  • #1742 — Introduce typed error classes with metadata (covers error taxonomy but not the raise-vs-return layering)
  • #698 — Tool.run should not reveal exception value to the client (security concern with current behavior)
  • #396 — Inconsistent Exception Handling in @app.call_tool (older, narrower scope)
  • #1788 — Extensible pattern for protocol flow-control exceptions

AI Disclaimer

贡献指南

打开贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

调研方向

从 src/mcp/server/mcpserver/server.py 中的 _handle_call_tool() 和 src/mcp/server/lowlevel/server.py 中的 _handle_request() 开始,比较它们的异常路径和响应构造方式。当高层处理器可以通过抛出异常来发出错误信号,低层处理器可以显式返回 ErrorData,并且任一层的未处理异常都能生成格式正确的 JSON-RPC 错误而不泄露内部细节时,这项工作就完成了。

由索引模型根据 Issue 内容生成。

评估

技术栈
python
领域
api, backend-api-design
Issue 类型
重构
难度
5/5
预计耗时
一周以上
活跃度
停滞
描述清晰度
基本清楚
新手友好度
35/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。