MCP codex_apps: Selected model is at capacity recurring error with available quota
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 125k
- Forks
- 19.4k
- PR merge metrics
- PR metrics pending
Description
What version of Codex CLI is running?
codex-cli 0.153.4
What subscription do you have?
plus
Which model were you using?
No response
What platform is your computer?
No response
What terminal emulator and version are you using (if applicable)?
No response
Codex doctor report
What issue are you seeing?
Describe the bug
Consistently get error:
Selected model is at capacity. Please try a different model.
This happens during MCP initialize / tool call phase against endpoint:
https://chatgpt.com/backend-api/ps/mcp
My account still has remaining Codex subscription quota, it is NOT quota exhaustion or rate‑limit reached.
The error occurs frequently even under low request frequency.
This is MCP client scenario(codex_rmcp_client), not official codex desktop/cli.
Reproduction steps
- Start MCP codex_apps server
- Send initialize request
- Receive capacity error response
Expected behavior
MCP session initialize normally, without capacity rejection when quota remains.
What steps can reproduce the bug?
Uploaded thread: 01a08056-c137-76a3-92d7-e93d0861e582
What is the expected behavior?
No response
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the codex_rmcp_client MCP initialize and tool-call flow, then review the uploaded thread 01a08056-c137-76a3-92d7-e93d0861e582. Reproduce against https://chatgpt.com/backend-api/ps/mcp using codex-cli 0.153.4 and a Plus account with remaining quota. Done means the recurring capacity rejection is reproduced and its handling is corrected or clearly isolated.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100