Release 01-25-2026 #3
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Updated logging configuration in `logging.py` to improve structured logging. - Refactored AzureOpenAIProvider in `provider.py` to build kwargs dynamically for better handling of optional parameters. - Introduced MCP server structure with new modules: `__init__.py`, `context.py`, `resources.py`, `server.py`, and `tools.py` for better organization and modularity. - Implemented resource registration for listing datasources and schemas in `resources.py`. - Added context management for MCP server in `context.py` to handle connections and state. - Created tools for executing queries, listing datasources, and validating SQL in `tools.py`. - Updated prompt handling by introducing a new `builder.py` for assembling prompts from components. - Added dialect-specific SQL guidelines in `dialects.py` to assist with query generation based on datasource type. - Enhanced default prompts in `defaults.py` to provide clearer instructions and context for users. - Improved response formatting in `response.py` and `data_nodes.py` for better user interaction. - Updated dependencies in `uv.lock` to include the new MCP package and ensure compatibility.
…into feature/mcp
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces support for the Model Context Protocol (MCP) for integration with Claude Desktop, VS Code, and other MCP clients, and refactors the agent workflow to add a "general chat" capability. It also improves prompt management by centralizing prompt templates and dialect guidelines, and updates documentation to reflect these changes. The most important changes are grouped below.
MCP Protocol Integration:
data-agent-mcp) and documentation for MCP server usage, options, available tools/resources, and client configuration for Claude Desktop, VS Code, and Cursor. [1] [2] [3] [4]Agent Workflow Refactor & General Chat:
Prompt Management Improvements:
promptsmodule, with documentation for usage, extension, and configuration overrides. Default prompts for intent detection and general chat are now imported and used in agent logic. [1] [2]Documentation and Config Updates:
Dependency and CLI Updates:
mcp>=1.25.0to dependencies and registered the MCP server CLI entrypoint inpyproject.toml.Let me know if you want a deeper dive into any of these changes!