ocr-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OCR_MCP_DATA_DIR | No | daemon 的 lock / socket / log 位置 | |
| OCR_MCP_LOG_LEVEL | No | 日志级别 | INFO |
| OCR_MCP_MODEL_DET | No | 检测模型 | PP-OCRv6_medium_det |
| OCR_MCP_MODEL_DIR | No | 自定义模型缓存目录（离线部署，会设置 PADDLEX_HOME） | |
| OCR_MCP_MODEL_REC | No | 识别模型 | PP-OCRv6_medium_rec |
| OCR_MCP_IDLE_TIMEOUT | No | daemon 空闲退出秒数 | 600 |
| OCR_MCP_REQUEST_TIMEOUT | No | 单次 OCR 请求超时秒数 | 60 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ocr_imageB | Recognize text in a local image file. Returns text + per-line confidence + coordinates. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of confusion or overlapping purpose. An agent can immediately identify the sole OCR action.
The single tool name, ocr_image, follows a clear snake_case convention. With only one tool, there is no inconsistency to evaluate.
A single tool for OCR is thin for the apparent domain. While it performs the core recognition action, typical OCR servers would benefit from additional operations such as batch processing or URL/PDF handling.
The core local-image OCR operation is present, but notable gaps exist. There is no support for batch files, alternate image sources, language selection, or configuration options that agents might reasonably expect.