mimo-vision
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Fallback API key used if MIMO_VISION_API_KEY, VISION_API_KEY, and OPENCODE_API_KEY are not set. | |
| VISION_API_KEY | No | Fallback API key used if MIMO_VISION_API_KEY is not set. | |
| OPENCODE_API_KEY | No | Fallback API key used if MIMO_VISION_API_KEY and VISION_API_KEY are not set. | |
| ANTHROPIC_API_KEY | No | Fallback API key used if MIMO_VISION_API_KEY, VISION_API_KEY, OPENCODE_API_KEY, and OPENAI_API_KEY are not set. | |
| MIMO_VISION_MODEL | No | Explicit model name. Setting this skips automatic route selection and disables fallback. | |
| MIMO_VISION_API_KEY | No | Explicit API key for the vision service (highest priority). If not set, other keys are tried in order. | |
| MIMO_VISION_BASE_URL | No | Explicit base URL for the vision API. Setting this skips automatic route selection and disables fallback. | |
| MIMO_VISION_ALLOW_PAID | No | Whether to allow the paid fallback route. Set to 'false', '0', 'no', or 'off' to disable. | true |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| describe_imageA | Describe an image file using a vision model and return a textual description. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusing it with another tool. The tool's purpose is clearly defined.
The single tool uses a clear verb_noun pattern ('describe_image'), which is consistent with common naming conventions. There are no other tool names to conflict.
Having only one tool for a vision-related server feels too few for the apparent scope. A vision server typically requires more capabilities such as image classification, object detection, or generation, making this single tool insufficient.
The tool surface is severely incomplete for a vision server. Relying solely on image description leaves many common vision tasks unaddressed, creating significant gaps that would cause agent failures.