OCR MCP
by Raffaele86
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_TILES | No | Maximum number of tiles (optional) | |
| TILE_OVERLAP | No | Overlap between tiles (optional) | |
| GLM_OCR_MODEL | Yes | Model name (e.g., glm-ocr or zai-org/GLM-OCR) | |
| GLM_OCR_API_KEY | Yes | API key for the OCR service | |
| MAX_TILE_HEIGHT | No | Maximum height of each tile (optional) | |
| GLM_OCR_BASE_URL | Yes | Base URL for the OCR API (e.g., https://api.z.ai/api/paas/v4 or http://<host-vllm>:8000) | |
| GLM_OCR_API_STYLE | Yes | API style: 'layout_parsing' for Zhipu or 'chat' for vLLM compatible endpoint |
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 | |
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues