docs: add AI-assisted contribution policy to CONTRIBUTING.md#2887
Conversation
Adds a disclosure requirement and autonomous-agent policy for AI-assisted contributions, aligned with the policy already in the spec repo. Also adds a corresponding entry to the 'What Gets Rejected' list.
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
There was a problem hiding this comment.
LGTM — straightforward docs-only addition of an AI-assisted contribution policy, with a correctly-matching internal anchor.
Extended reasoning...
Overview
This PR makes a single documentation change to CONTRIBUTING.md: it adds an "AI-Assisted Contributions" section (disclosure requirement, human-accountability expectation, no-autonomous-agents rule) and a corresponding bullet in the "What Gets Rejected" list that links back to the new section. No source code, configuration, build, or test files are touched.
Security risks
None. This is prose in a contributor-facing markdown file. There is no executable code, no dependency change, and nothing that affects runtime behavior, auth, crypto, or data handling.
Level of scrutiny
Minimal scrutiny is warranted. The only correctness concern for a docs change like this is link/anchor integrity, and the new "What Gets Rejected" entry links to #ai-assisted-contributions, which is the correctly slugified form of the new ### AI-Assisted Contributions heading. Markdown is well-formed and the PR notes markdownlint passes via pre-commit.
Other factors
The change is small, self-contained, and aligns with an existing policy in the spec repo. No bugs were reported by the bug-hunting system, and the timeline contains no unaddressed reviewer feedback. This meets the bar for shadow approval.
2 participants
Adds an "AI-Assisted Contributions" section to
CONTRIBUTING.mdrequiring disclosure of AI use, human accountability for submitted changes, and stating that autonomous-agent PRs/issues/comments will be closed without review. Also adds a matching entry to the "What Gets Rejected" list.Motivation and Context
The volume of unreviewed AI-generated PRs and issue comments has become a real maintenance burden. The spec repo already has a disclosure policy (added in modelcontextprotocol/modelcontextprotocol#2162) but it was never propagated to the SDK repos. This brings python-sdk in line with that, with slightly more direct wording around autonomous agents.
How Has This Been Tested?
markdownlint passes via pre-commit.
Breaking Changes
None.
Types of changes
Checklist
AI Disclaimer