openai-vision-mcp-server
by ygq-future
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | Yes | Vision model name (e.g., gpt-4o, qwen-vl-max, claude-3-5-sonnet). | |
| VISION_API_KEY | Yes | API key for authentication. | |
| VISION_BASE_URL | Yes | Base URL of the OpenAI-compatible API (e.g., https://api.openai.com/v1). | |
| VISION_MAX_REDIRECTS | No | Maximum HTTP redirect count. Default: 3. | 3 |
| VISION_HTTP_TIMEOUT_MS | No | HTTP request timeout in milliseconds. Default: 15000. | 15000 |
| VISION_MAX_CONCURRENCY | No | Max concurrent tile processing calls. Default: 2. | 2 |
| VISION_MAX_INPUT_BYTES | No | Max raw image download size in bytes. Default: 20971520. | 20971520 |
| VISION_DEFAULT_MAX_TILES | No | Default hard ceiling for detail tiles (1 to 64). Default: 24. | 24 |
| VISION_ALLOWED_FILE_ROOTS | No | Delimiter-separated absolute paths allowed for file:// URIs. Default: "". | |
| VISION_MAX_DECODED_PIXELS | No | Max allowed total decoded image pixels. Default: 40000000. | 40000000 |
| VISION_ALLOW_PRIVATE_NETWORK | No | Set to 'true' to allow http(s):// fetches targeting private/internal IPs. Default: false. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessWithin a week