Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_URLNoOllama endpointhttp://127.0.0.1:11434
PHOTO_OCR_MODELNoModel for VLM OCRminicpm-v
PHOTO_VLM_MODELNoModel for analysis, scene inspection, comparisonqwen3-vl:8b
PHOTO_VLM_MAX_DIMNoDownscale longest side before inference2048
PHOTO_VLM_TIMEOUTNoOllama request timeout in seconds120
PHOTO_VLM_KEEP_ALIVENoOllama keep-alive setting10m
PHOTO_VLM_MAX_TOKENSNoDefault generation limit1024
PHOTO_VLM_MAX_IMAGE_MBNoReject larger images20
PHOTO_VLM_ALLOWED_ROOTSNoOptional path allow-list, separated by ; on Windows or : elsewhere
PHOTO_VLM_FETCH_TIMEOUTNoURL fetch timeout15
PHOTO_VLM_ALLOW_PRIVATE_URLSNoAllow private/loopback URLs0

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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/YehudRaanan/photo-vlm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server