Feat/add insforge + supabase mcp support to evaluate against postgres#214
Merged
zjwu0522 merged 5 commits intoeval-sys:mainfrom Oct 31, 2025
Merged
Conversation
Adds complete support for benchmarking Insforge Backend-as-a-Service via MCP. ## What's Added: - **Insforge MCP Service**: New service configuration in `src/services.py` - **State Management**: `InsforgeStateManager` handles backend setup via `prepare_environment.py` scripts - **Login Helper**: `InsforgeLoginHelper` validates backend connectivity - **Task Manager**: `InsforgeTaskManager` manages Insforge-specific tasks - **MCP Integration**: Added Insforge to both `base_agent.py` and `mcpmark_agent.py` - **Docker Support**: Updated `run-task.sh` with Insforge container configuration ## How It Works: - Uses `@insforge/mcp` npm package for MCP server - Requires `INSFORGE_API_KEY` and `INSFORGE_BACKEND_URL` environment variables - Can test SQL tasks by symlinking `tasks/insforge -> tasks/postgres` - Enables comparison between direct SQL (postgres-mcp) and REST API (insforge) approaches ## Configuration: ```bash # In .mcp_env INSFORGE_API_KEY="your-api-key" INSFORGE_BACKEND_URL="http://localhost:7130" ``` ## Usage: ```bash python -m pipeline \ --mcp insforge \ --models claude-sonnet-4 \ --exp-name insforge-test \ --tasks your_task \ --k 1 ``` 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
tonychang04
changed the title
Collaborator
|
Thanks for PR! We will look into this asap. |
zjwu0522
approved these changes
Oct 29, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Change Type
Description of Change
test:
opened supabase cli and tested the dataset
opened insforge local host version and tested the dataaset
python -m pipeline
--mcp supabase
--models claude-sonnet-4.5
--exp-name supabase-comprehensive-sonnet45
--tasks all
--k 4
python -m pipeline \
--mcp insforge \ --models claude-sonnet-4.5 \
--exp-name insforge-comprehensive-sonnet45
--tasks all
--k 4
Additional Information
This is the benchmark results. We can also provide the runs and the files!