Skip to main content
Glama

ThinkDrop Vision Service

by lukaizhi5559

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoThe port on which the service runs3006
API_KEYYesYour vision API key
VLM_MODELNoThe VLM model to useopenbmb/MiniCPM-V-2_6
OCR_ENGINENoThe OCR engine to usepaddleocr
VLM_DEVICENoThe device to use for VLM (auto, cpu, cuda)auto
VLM_ENABLEDNoEnable or disable VLM (lazy-loaded)true
OCR_LANGUAGENoThe language for OCRen
USER_MEMORY_API_KEYNoAPI key for the user memory service
WATCH_CHANGE_THRESHOLDNoChange threshold for watch mode0.08
USER_MEMORY_SERVICE_URLNoURL of the user memory servicehttp://localhost:3003
WATCH_DEFAULT_INTERVAL_MSNoDefault interval for watch mode in milliseconds2000

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/lukaizhi5559/thinkdrop-vision-service'

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