Atlas Vision MCP
by QuangThai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | Vision model ID | gpt-4o-mini |
| VISION_API_KEY | Yes | Provider credential (required for live calls) | |
| VISION_BASE_URL | No | Provider API base URL | https://api.openai.com/v1 |
| VISION_PROVIDER | No | Vision adapter (provider choice) | openai-compatible |
| ATLAS_ALLOWED_DIRS | No | Comma-separated list of readable root directories | . |
| ATLAS_STORE_HISTORY | No | No persistence by default | false |
| VISION_MAX_IMAGE_MB | No | Maximum image size in MB before resizing | 10 |
| ATLAS_REDACT_SECRETS | No | Redact likely secrets in OCR output | true |
| ATLAS_LOG_IMAGE_CONTENT | No | Do not log image bytes/text by default | false |
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/QuangThai/vision-bridge-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server