feat(tool): add Xquik search and bound scrape requests

[kriptoburak]

Describe this PR

Adds an opt-in FastMCP tool for cursor-paginated X post search through Xquik.

What changed?

• Added tool-xquik configuration with environment-based credentials.
• Added search_x_tweets with input and response validation.
• Added sanitized HTTP and network error handling.
• Added focused tests and tool documentation.
• Fixed an independent reliability defect in the existing direct scrape fallback: requests previously had no timeout and could hang an agent indefinitely. Direct requests now use a tested 30-second bound with an explicit override.

Why?

MiroFlow agents can now search X data through the existing MCP tool boundary. The integration is opt-in and does not change the default tool set. The timeout repair also keeps unrelated fallback scraping from stalling an agent run forever.

Related issues

None.

Checklist for PR

• Descriptive Angular-format PR title.
• uvx --from ruff==0.8.0 ruff check .
• uvx --from ruff==0.8.0 ruff format --check .
• uv run --python 3.12 python -m unittest discover -s tests -p "test_*.py" (9 tests)
• MkDocs build
• Xquik public contract and link checks

Xquik is an independent third-party service. Not affiliated with X Corp. "Twitter" and "X" are trademarks of X Corp.