AI Vision MCP Server
by honeyvig
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_TOKENS | No | General maximum tokens for AI responses | 1500 |
| TEMPERATURE | No | General temperature setting for AI responses | 0.7 |
| GEMINI_API_KEY | No | Your Google AI Studio API key for using the google provider | |
| IMAGE_PROVIDER | No | The provider to use for image analysis (google or vertex_ai) | |
| VIDEO_PROVIDER | No | The provider to use for video analysis (google or vertex_ai) | |
| GCS_BUCKET_NAME | No | Your Google Cloud Storage bucket name for Vertex AI | |
| VERTEX_CREDENTIALS | No | Path to the service account JSON file for Vertex AI authentication | |
| ANALYZE_IMAGE_MODEL | No | Model to use for analyze_image function | |
| ANALYZE_VIDEO_MODEL | No | Model to use for analyze_video function | |
| COMPARE_IMAGES_MODEL | No | Model to use for compare_images function | |
| TEMPERATURE_FOR_IMAGE | No | Task-specific temperature for image analysis | 0.2 |
| TEMPERATURE_FOR_VIDEO | No | Task-specific temperature for video analysis | 0.5 |
| TEMPERATURE_FOR_ANALYZE_IMAGE | No | Function-specific temperature for analyze_image | 0.1 |
| TEMPERATURE_FOR_COMPARE_IMAGES | No | Function-specific temperature for compare_images | 0.3 |
| TOP_K_FOR_DETECT_OBJECTS_IN_IMAGE | No | Vocabulary selection for detect_objects_in_image | 30 |
| TOP_P_FOR_DETECT_OBJECTS_IN_IMAGE | No | Nucleus sampling for detect_objects_in_image | 0.95 |
| MAX_TOKENS_FOR_DETECT_OBJECTS_IN_IMAGE | No | High token limit for JSON responses in detect_objects_in_image | 8192 |
| TEMPERATURE_FOR_DETECT_OBJECTS_IN_IMAGE | No | Function-specific temperature for detect_objects_in_image (deterministic responses) | 0.0 |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/honeyvig/ai-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server