Hybrid Vision MCP Server
by sameersemna
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Express listener port. | 11402 |
| UPLOAD_DIR | No | Directory for temporary binary image uploads. | /tmp/hvm-uploads |
| OLLAMA_HOST | No | Base URL for the local Ollama inference service. | http://localhost:11434 |
| CORS_ORIGINS | No | Comma-separated list of allowed CORS origins for the /upload endpoint. | |
| DOWNLOAD_DIR | No | Directory for downloaded images from URLs. | ./tmp/hvm-downloads |
| FEEDBACK_DIR | No | Directory for saved output images (annotations, diffs, overlays). | /tmp/hvm-feedback |
| OLLAMA_TIMEOUT_MS | No | Timeout for Ollama vision requests in milliseconds. | 180000 |
| UPLOAD_RATE_LIMIT | No | Maximum upload requests per minute per client IP. | 10 |
| VISION_MODEL_FAST | No | Default vision model for analyze_image and detect_ui_elements. | llava:13b |
| ALLOWED_REPO_ROOTS | No | Comma-separated list of absolute directory paths that generate_repo_graph is permitted to walk. | server's own project directory |
| MAX_UPLOAD_SIZE_MB | No | Maximum upload size in megabytes. | 20 |
| VISION_MODEL_HEAVY | No | Default vision model for find_text_element, compare_images, browser_screenshot_analysis, visual_diff, and detect_ui_elements. | qwen3-vl:30b |
| MAX_DOWNLOAD_SIZE_MB | No | Maximum download size in megabytes for URL-based image downloads. | 50 |
| MAX_OLLAMA_QUEUE_SIZE | No | Maximum number of requests allowed to wait for a free Ollama slot before new ones are rejected outright. | 20 |
| MCP_REQUEST_TIMEOUT_MS | No | Timeout for MCP client request/response in milliseconds. | 300000 |
| MAX_PARALLEL_OLLAMA_REQUESTS | No | Maximum number of Ollama vision requests allowed to run concurrently. | 1 |
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/sameersemna/hybrid-vision-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server