Add MCP server for AI-assisted model customization#55
Open
YarivLevy81 wants to merge 1 commit intoaws:mainfrom
Open
Add MCP server for AI-assisted model customization#55YarivLevy81 wants to merge 1 commit intoaws:mainfrom
YarivLevy81 wants to merge 1 commit intoaws:mainfrom
Conversation
Adds an optional MCP (Model Context Protocol) server that exposes Nova Forge SDK operations as tools for AI assistants. Includes tools for training, evaluation, deployment, job status, log retrieval, and dataset validation. Install with pip install "amzn-nova-forge[mcp]".
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds an optional MCP (Model Context Protocol) server that exposes Nova Forge SDK operations as tools for AI assistants like Claude. Install with
pip install "amzn-nova-forge[mcp]".7 tools exposed:
train— Launch fine-tuning jobs (SFT, DPO, CPT, RFT)evaluate— Run model evaluation (MMLU, BBH, GPQA, etc.)deploy— Deploy to SageMaker or Bedrockget_job_status— Check job status via SageMaker/Bedrock APIsget_logs— Retrieve CloudWatch logs for jobsvalidate_dataset— Validate JSONL datasets before traininglist_options— List available models, methods, platforms, and eval tasksChanges:
src/amzn_nova_forge/mcp/server.py— MCP server with 7 tools wrapping the SDK's stateful API into flat, JSON-friendly tool callssrc/amzn_nova_forge/mcp/__init__.py— Module entry pointpyproject.toml— Addedmcpoptional dependency (fastmcp>=2.0) andnova-forge-mcpconsole scriptREADME.md— Added MCP Server section with install, config (Claude Desktop/Code), and usage docstests/mcp/test_server.py— 40 unit tests across 10 test classes covering all tools and helpers