agent-vision-mcp
by idealizing
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OCR_ENABLED | No | Set to 'true' to enable dedicated OCR. Disabled by default. | false |
| VISION_API_KEY | Yes | API key for the OpenAI-compatible multimodal endpoint. | |
| VISION_BASE_URL | Yes | Base URL for the vision model provider (e.g., https://your-provider.example/v1). | |
| VISION_MODEL_ID | Yes | Identifier of the vision model to use. | |
| VISION_URL_MODE | No | Controls how remote images are sent to the model. Options: auto, passthrough, download. Default: auto. | auto |
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
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/idealizing/agent-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server