modelcontextprotocol / modelcontextprotocol/servers

"Invalid prompt: your prompt was flagged as potentially violating our usage policy" after GPT-5.5 uses Sequential Thinking

Open
#4,031 1 comment 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
90.5k
Forks
11.7k
Avg merge
2d 2h
Merged PRs (30d)
5

Description

This has never occurred before and has happened twice now after starting to us GPT-5.5. This never occurred before using previous GPT models

Here is what it shows. I am not sure how to pull the logs to check what exactly is causing this behavior:
"Using Sequential Thinking
Sequentialthinking
Invalid prompt: your prompt was flagged as potentially violating our usage policy. Please try again with a different prompt: https://platform.openai.com/docs/guides/reasoning#advice-on-prompting"

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the failure with GPT-5.5 and the Sequential Thinking server. Gather the relevant logs or request details, since the issue currently provides no file, test, or exact prompt. Done means the cause of the policy rejection is identified and the affected behavior is covered by a reproducible verification.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.