vision-opencode-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VISION_MODEL | No | Vision model name. | mimo-v2.5-free |
| VISION_API_KEY | Yes | API key for the vision endpoint. Required. | |
| VISION_TIMEOUT | No | HTTP timeout in ms. | 180000 |
| VISION_API_BASE | No | Base URL of the OpenAI-compatible API. | http://opencode.ai/zen/v1 |
| VISION_MAX_TOKENS | No | max_tokens for the completion (thinking models need headroom). | 8192 |
| VISION_PASTED_DIR | No | Directory scanned for the newest image when image_path is empty. | %TEMP%\opencode\pasted_images |
| VISION_USER_AGENT | No | Sent as User-Agent; some endpoints (Cloudflare-protected) return 403 without a browser UA. | Chrome UA |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| vision_describeA | Give the model visual reference: read a local image file and return what a vision-capable model sees/understands about it. Use whenever you need to see or interpret an image (screenshots, diagrams, photos). |
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 confusion or overlap. The tool's purpose is clearly described and distinct by virtue of being the only option.
The single tool name 'vision_describe' follows a consistent verb_noun pattern. With only one tool, internal naming consistency is trivially maintained.
One tool is borderline thin for a server whose name suggests broader vision capabilities. However, the narrow focus on image description makes the count acceptable, if minimal.
The tool covers the core need of interpreting local image files, but lacks support for remote images or additional vision operations (e.g., OCR, image metadata). These are minor gaps for the stated purpose.