Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MAX_TILESNoMaximum number of tiles (optional)
TILE_OVERLAPNoOverlap between tiles (optional)
GLM_OCR_MODELYesModel name (e.g., glm-ocr or zai-org/GLM-OCR)
GLM_OCR_API_KEYYesAPI key for the OCR service
MAX_TILE_HEIGHTNoMaximum height of each tile (optional)
GLM_OCR_BASE_URLYesBase URL for the OCR API (e.g., https://api.z.ai/api/paas/v4 or http://<host-vllm>:8000)
GLM_OCR_API_STYLEYesAPI style: 'layout_parsing' for Zhipu or 'chat' for vLLM compatible endpoint

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/Raffaele86/ocr-mcp'

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