openai / openai/codex

API quickstart remote MCP example uses a retired endpoint that returns 404

Open
#44,563 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

documentation mcp
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What is the type of issue?

Example code is not working

What is the issue?
Problem

The remote MCP quickstart example points to https://dmcp-server.deno.dev/mcp, which no longer serves its deployment. This prevents the documented “Roll 2d4+1” example from working.

The same URL appears across the language examples.

Reproduction
curl -i https://dmcp-server.deno.dev/mcp

Verified September 10, 2026:

HTTP/2 404

404: Not Found (DEPLOYMENT_NOT_FOUND)

The requested deployment does not exist. Deno Deploy Classic was sunset on July 20, 2026 and no longer serves deployments. See https://deno.com/deploy for the new Deno Deploy.

An MCP initialize POST request also returns the same 404.

Expected behavior

The quickstart should use a working MCP endpoint so users can successfully run the example.

Suggested fix
  • Point all language examples to a maintained, publicly accessible MCP endpoint.
  • Update the server description and prompt if the replacement endpoint provides different tools.
  • Verify the example end to end through the Responses API.
Where did you find it?

https://developers.openai.com/api/docs/quickstart?lang=python&tool-type=remote-mcp#extend-the-model-with-tools

The same URL appears across the language examples.

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 with the linked remote MCP quickstart and search the language examples for dmcp-server.deno.dev/mcp. Test a maintained replacement with the curl and MCP initialize requests described in the issue, then verify the example end to end through the Responses API. Done means every language example uses a working endpoint and its server description and prompt match the replacement tools.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, documentation
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.