Codex Imagem

by mcp-dirio.github.mcp-dir/codex_image-mcpv0.1.0

How the score works

Generate images with your own ChatGPT subscription (Plus, Pro or Team), without spending API credits

  • Remote endpoint

Uptime

Checked  · every day

99.83%from 11 days of checks

Up without downtime on 9 of 11 days with data; down 25 minutes in all, the longest 15 minutes on 7 November.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 5044 ms, slowest 5% 13315 ms for the handshake and the tool list, over 30 days.

10000 ms5000 ms0

How far each check got

  • Reached the address 52.0%
  • Completed the handshake 48.0%
  • Listed its tools 48.0%

8 tools at the last answer.

Every day
DayResultChecksMedian
10 Nov (today)Down 10 minutes31758 ms
9 NovNo downtime2of 18925 ms
8 NovNo downtime2of 18293 ms
7 NovDown 15 minutes4of 11308 ms
6 NovNo downtime2of 16567 ms
5 NovNo downtime2of 17662 ms
4 NovSlow answers2of 110836 ms
3 NovNo downtime1of 13219 ms
2 NovNo downtime2of 17936 ms
1 NovNo downtime2of 11636 ms
31 OctNo downtime31543 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Run in a terminal:

claude mcp add --transport http codex_image-mcp https://api.mcp.ai/p_codex_image
For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server Codex Imagem (`io.github.mcp-dir/codex_image-mcp`)

Its page: https://plug.directory/servers/io.github.mcp-dir/codex_image-mcp

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://api.mcp.ai/p_codex_image
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport http codex_image-mcp https://api.mcp.ai/p_codex_image
```

## Cursor, Devin Desktop, LM Studio, oterm, Bob Shell, ECA, Kiro, Kiro CLI

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- Bob Shell: ~/.bob/settings/mcp.json (global) or .bob/mcp.json (project)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project
- Kiro: ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace)
- Kiro CLI: ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace)

```json
{
  "mcpServers": {
    "codex_image-mcp": {
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "codex_image-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Zed

Merge into ~/.config/zed/settings.json:

```json
{
  "context_servers": {
    "codex_image-mcp": {
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Cline

Merge into cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers):

```json
{
  "mcpServers": {
    "codex_image-mcp": {
      "type": "streamableHttp",
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "codex_image-mcp"
    type: streamable-http
    url: "https://api.mcp.ai/p_codex_image"
```

## Goose

Merge into ~/.config/goose/config.yaml:

```yaml
extensions:
  "codex_image-mcp":
    type: streamable_http
    name: "codex_image-mcp"
    enabled: true
    uri: "https://api.mcp.ai/p_codex_image"
    headers: {}
    env_keys: []
    envs: {}
    timeout: 300
```

## Gemini CLI

Merge into ~/.gemini/settings.json:

```json
{
  "mcpServers": {
    "codex_image-mcp": {
      "httpUrl": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Codex

Run in a terminal:

```sh
codex mcp add codex_image-mcp --url https://api.mcp.ai/p_codex_image
```

## mcp-client-cli, TUUI, BoltAI

This server's endpoint speaks streamable HTTP, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

Merge into ~/.config/agenvoy/mcp.json:

```json
{
  "servers": {
    "codex_image-mcp": {
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "codex_image-mcp": {
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## AnythingLLM

Merge into anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory:

```json
{
  "mcpServers": {
    "codex_image-mcp": {
      "type": "streamable",
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

## Augment Code

Merge into Augment Settings Panel – MCP section – Import from JSON (VS Code extension):

```json
{
  "mcpServers": {
    "codex_image-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_codex_image"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

From the publisher's entry in the Official MCP Registry (the registry entry). Report a problem