Expose DAG validation as LLM tools via MCP

[Dev-iL]

Changes

This includes 6 tools that leverage Hamilton's compile-time DAG validation for LLM feedback loops:

1. validate_dag - Validate Hamilton DAG code by building the Driver.
2. list_nodes - List all nodes in a Hamilton DAG with their types and dependencies.
3. visualize - Visualize the Hamilton DAG as DOT graph source.
4. execute - Execute a Hamilton DAG and return the requested outputs.
5. get_docs - Get Hamilton documentation for a specific topic.
6. scaffold - Generate a starter Hamilton module for a given pattern.

How I tested this

• The included unit tests.
• Claude code:

Notes

To use:

uv pip install .[mcp]
# Below for Claude, for other tools see the fastmcp v3 docs
fastmcp install claude-code hamilton/plugins/h_mcp/server.py

Checklist

• PR has an informative and human-readable title (this will be pulled into the release notes)
• Changes are limited to a single goal (no scope creep)
• Code passed the pre-commit check & code is left cleaner/nicer than when first encountered.
• Any change in functionality is tested
• New functions are documented (with a description, list of inputs, and expected output)
• Placeholder code is flagged / future TODOs are captured in comments
• Project documentation has been updated if adding/changing functionality.

[skrawcz]

just one change