codex-vision-mcp
by lyd123qw2008
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CODEX_JS | No | Full path to @openai/codex/bin/codex.js | |
| CODEX_BIN | No | Command or executable to start Codex | |
| CODEX_VISION_MODEL | No | Model for Codex app-server | gpt-5.4 |
| CODEX_VISION_WORKDIR | No | Base directory for relative image paths | |
| CODEX_VISION_MAX_IMAGES | No | Max images per call | 5 |
| CODEX_VISION_TIMEOUT_MS | No | Request timeout in milliseconds | 180000 |
| CODEX_VISION_MAX_IMAGE_MB | No | Max local image size in MB | 20 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lyd123qw2008/codex-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server