Add ValidationOptions for lenient output schema validation

[lorenss-m]

Motivation and Context

Currently, MCP clients raise RuntimeError when tools don't return structured content matching their outputSchema. This breaks integrations with servers that have schema/implementation mismatches.

This PR adds optional lenient validation that converts these errors to warnings, allowing clients to continue operating with imperfect servers.

How Has This Been Tested?

• Added test suite in tests/client/test_validation_options.py
• All existing tests pass
• Tested with real MCP servers exhibiting validation issues

Breaking Changes

None. Default behavior unchanged. Lenient validation is opt-in:

from mcp.client.session import ValidationOptions

# Opt-in to lenient validation
options = ValidationOptions(strict_output_validation=False)
session = ClientSession(read, write, validation_options=options)

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Documentation update

Checklist

• I have read the MCP Documentation
• My code follows the repository's style guidelines
• New and existing tests pass locally
• I have added appropriate error handling
• I have added or updated documentation as needed

Additional context

• Added ValidationOptions class following existing patterns (e.g., TransportSecuritySettings)
• Modified ClientSession.call_tool() to check options before raising validation errors
• Fixed workspace config issue with structured_output_lowlevel.py by creating proper package structure

[ochafik]

Hi @lorenss-m, thanks for sending this!

Seems reasonable to add this option given the spec only says clients "should" validate structured results against the output schema.

I'm curious tho, which examples of non-conforming outputs did you find / how bad were they?

cc/ @bhosmer-ant since authored initial support in #993

[ochafik]

What error would None produce here, do we need the two branches?

[ochafik]

Wondering if we wanna make this sound more explicitly about tool call output, as there's also validation happening around elicitation (https://modelcontextprotocol.io/specification/2025-06-18/client/elicitation#security-considerations)

Maybe something like validate_structured_outputs (no sure we need strict in the name, if we don't raise an exception the output isn't really validated, warnings being often ignored)

[ochafik]

nit: might wanna raise ... from e