raise ValueError(str(e)) discards exception chain in get_prompt handler

[blackwell-systems]

Initial Checks

• I confirm that I'm using the latest version of MCP Python SDK
• I confirm that I searched for my issue in https://github.com/modelcontextprotocol/python-sdk/issues before opening this issue

Description

In server/mcpserver/server.py, the get_prompt handler catches all exceptions and re-raises as ValueError(str(e)) without chaining:

Line 1110-1112:

except Exception as e:
    logger.exception(f"Error getting prompt {name}")
    raise ValueError(str(e))

This discards the original exception's type, traceback, and identity. Callers cannot use isinstance() or __cause__ to determine what went wrong.

The same file uses the correct pattern eight lines earlier (line 459):

raise ResourceError(f"Error reading resource {uri}") from exc

A second instance at line 451 also omits from:

except ValueError:
    raise ResourceError(f"Unknown resource: {uri}")

Fix

# Line 1112
raise ValueError(str(e)) from e

# Line 451
except ValueError as exc:
    raise ResourceError(f"Unknown resource: {uri}") from exc

Impact

Without from, Python shows "During handling of the above exception, another exception occurred" which is confusing. With from, it shows "The above exception was the direct cause of the following exception" and preserves __cause__ for programmatic inspection.