Skip to content

Commit 32c065d

Browse files
authored
Merge pull request modelcontextprotocol#1598 from modelcontextprotocol/localden/contrib
(docs): Update contribution guidelines around AI usage for PRs/issues
2 parents 266e9a8 + 099075b commit 32c065d

File tree

1 file changed

+49
-0
lines changed

1 file changed

+49
-0
lines changed

CONTRIBUTING.md

Lines changed: 49 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -121,6 +121,55 @@ When contributing to the documentation:
121121
3. Follow the pull request template
122122
4. Wait for review
123123

124+
## AI Contributions
125+
126+
> [!IMPORTANT]
127+
>
128+
> If you are using **any kind of AI assistance** to contribute to Model Context Protocol,
129+
> it must be disclosed in the pull request or issue.
130+
131+
We welcome and encourage the use of AI tools to help improve Model Context Protocol. Many valuable contributions
132+
have been enhanced with AI assistance for code generation, issue detection, and feature definition.
133+
134+
That being said, if you are using any kind of AI assistance (e.g., agents such as Claude Code, ChatGPT)
135+
while contributing to Model Context Protocol, **this must be disclosed in the pull request or issue**,
136+
along with the extent to which AI assistance was used (e.g., documentation comments vs. code generation).
137+
138+
If your PR responses or comments are being generated by an AI, disclose that as well.
139+
140+
As an exception, trivial spacing or typo fixes don't need to be disclosed, so long as the changes are
141+
limited to small parts of the code or short phrases.
142+
143+
An example disclosure:
144+
145+
> This PR was written primarily by Claude Code.
146+
147+
Or a more detailed disclosure:
148+
149+
> I consulted ChatGPT to understand the codebase but the solution
150+
> was fully authored manually by myself.
151+
152+
Failure to disclose this is first and foremost rude to the human operators on the other end of the pull request,
153+
but it also makes it difficult to determine how much scrutiny to apply to the contribution.
154+
155+
In a perfect world, AI assistance would produce equal or higher quality work than any human. That isn't the world
156+
we live in today, and in most cases where human supervision or expertise is not in the loop, it's generating code
157+
or changes that cannot be reasonably maintained or evolved.
158+
159+
### What we're looking for
160+
161+
When submitting AI-assisted contributions, please ensure they include:
162+
163+
- **Clear disclosure of AI use** - You are transparent about AI use and degree to which you're using it for the contribution
164+
- **Human understanding** - You personally understand what the changes do
165+
- **Clear rationale** - You can explain why the change is needed and how it fits within Model Context Protocol goals
166+
- **Concrete evidence** - Include test cases, scenarios, or examples that demonstrate the improvement
167+
- **Your own analysis** - Share your thoughts on the end-to-end experience
168+
169+
### What we'll close
170+
171+
We reserve the right to close submissions that appear to not follow the disclosure policy.
172+
124173
## License
125174

126175
By contributing, you agree that your contributions will be licensed under the MIT

0 commit comments

Comments
 (0)