vision-bridge-mcp
by Catapult291
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODE_OPTIONS | No | Optional Node.js CLI options, e.g. --dns-result-order=ipv4first for Windows IPv6 routing issues | |
| VISION_MODEL | Yes | Vision model name, e.g. gpt-4o | |
| VISION_API_KEY | Yes | API key for the vision model provider | |
| VISION_CACHE_DIR | No | Cache directory, default ./.cache | ./.cache |
| VISION_CACHE_TTL | No | Cache TTL in seconds, default 3600; 0 or negative disables caching | 3600 |
| VISION_API_FORMAT | No | Request protocol: openai (default) or anthropic | openai |
| VISION_MAX_TOKENS | No | Max output tokens per call, default 2048 | 2048 |
| VISION_API_BASE_URL | Yes | Vision model API base URL. OpenAI: usually ends with /v1; Anthropic: base without /v1 (auto-appends /v1/messages). For example: https://api.openai.com/v1 or https://api.anthropic.com/ |
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
ActivitySlowing
ResponsivenessNo issues