feat(mcp): add pipeline code generation tool to MCP

[devin-ai-integration]

feat(mcp): add pipeline generation tool to dev operations

This PR targets the following PR:

• feat: add experimental MCP server to PyAirbyte, add secrets references and secrets hydration features #696

---

Summary

Adds a new MCP tool generate_pyairbyte_pipeline that generates complete PyAirbyte pipeline scripts with setup instructions. The implementation uses a template-based approach (no external AI dependencies) and integrates with the existing MCP server architecture.

Key Changes:

• Created new _local_dev.py module for development-focused MCP tools
• Added generate_pyairbyte_pipeline function that generates pipeline code and setup instructions
• Updated MCP server to register the new development tools
• Uses template-based code generation with connector validation

Review & Testing Checklist for Human

• Test MCP tool end-to-end: Verify the tool is actually callable through the MCP server and returns expected results
• Validate generated pipeline code: Check that the generated Python code is syntactically correct and uses proper PyAirbyte patterns
• Test connector validation: Ensure get_available_connectors() works correctly in the MCP server context and validates input connectors
• Verify setup instructions accuracy: Review that the generated setup instructions are complete and accurate for users
• Check f-string escaping: Ensure the template f-strings with double braces ({{}}) render correctly without escaping issues

Recommended Test Plan:

1. Start the MCP server and confirm it loads without errors
2. Call the generate_pyairbyte_pipeline tool with valid connectors (e.g., 'source-faker', 'destination-duckdb')
3. Save the generated code to a file and verify it's syntactically valid Python
4. Follow the generated setup instructions to ensure they work correctly
5. Test error handling with invalid connector names

---

Diagram

graph TD
    A[airbyte/mcp/server.py]:::minor-edit --> B[register_local_dev_tools]
    B --> C[airbyte/mcp/_local_dev.py]:::major-edit
    C --> D[generate_pyairbyte_pipeline]
    D --> E[get_available_connectors]:::context
    D --> F[Template Generation]
    F --> G[Pipeline Code]
    F --> H[Setup Instructions]
    
    I[airbyte/mcp/_local_ops.py]:::context
    J[airbyte/mcp/_connector_registry.py]:::context
    K[airbyte/mcp/_cloud_ops.py]:::context
    
    A --> I
    A --> J  
    A --> K
    
    subgraph Legend
        L1[Major Edit]:::major-edit
        L2[Minor Edit]:::minor-edit
        L3[Context/No Edit]:::context
    end
    
    classDef major-edit fill:#90EE90
    classDef minor-edit fill:#87CEEB
    classDef context fill:#FFFFFF

Loading

Notes

• Environment Testing Limitation: Local testing was blocked by dependency issues (missing 'six' module), so end-to-end validation is crucial during review
• Template Approach: Switched from OpenAI-based generation to template-based as requested, which simplifies dependencies but requires validation of generated code quality
• Linting: Two remaining linting warnings for long documentation URLs (E501) were left as-is since they're in documentation strings
• MCP Integration: Follows existing patterns from other MCP modules but integration should be verified in practice

Link to Devin run: https://app.devin.ai/sessions/eb48d57494b64683b1f0ad9fb940746f
Requested by: Aaron ("AJ") Steers (@aaronsteers)

[devin-ai-integration]

Original prompt from AJ Steers:

@Devin - Can you adapt '`generate_pyairbyte_pipeline'` from this gist: <https://gist.github.com/aaronsteers/2246450598aa4f103f38958f1e26490f>

into a stacked PR on top of this PR: <https://github.com/airbytehq/PyAirbyte/pull/696>

[devin-ai-integration]

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

• Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
• Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

• Disable automatic comment and CI monitoring

[github-actions]

PyTest Results (Fast Tests Only, No Creds)

693 tests  ±0   693 ✅ ±0   18m 10s ⏱️ +40s
  1 suites ±0     0 💤 ±0 
  1 files   ±0     0 ❌ ±0 

Results for commit 61f68e5. ± Comparison against base commit bd299ee.

♻️ This comment has been updated with latest results.

[github-actions]

PyTest Results (Full)

755 tests  ±0   741 ✅ ±0   31m 21s ⏱️ -24s
  1 suites ±0    14 💤 ±0 
  1 files   ±0     0 ❌ ±0 

Results for commit 61f68e5. ± Comparison against base commit bd299ee.

♻️ This comment has been updated with latest results.

[devin-ai-integration]

Closing due to inactivity for more than 7 days. Configure here.