Image Label MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LABEL_API_URL | No | API base URL, for another deployment or `sam local start-api` | https://labels.sachin-kale.com/api |
| LABEL_PASSWORD | No | Account password. Without credentials requests are anonymous and read-only in practice. | |
| LABEL_USERNAME | No | Account username. Without credentials requests are anonymous and read-only in practice. |
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 |
|---|---|
| list_imagesA | List images saved in Image Label, optionally filtered by category (case-insensitive). Returns summaries; use get_image for annotations and the viewing URL. |
| get_imageA | Get one image's metadata, all annotations, and a signed viewing URL (valid 24h). |
| update_image_metadataA | Update an image's name, category, sub-category or description. Omitted fields are left unchanged. |
| add_annotationsB | Append annotations to an image, keeping the existing ones. |
| replace_annotationsA | Replace ALL annotations on an image with the given list. Pass an empty list to clear them. |
| remove_annotationsC | Remove specific annotations from an image by their ids. |
| upload_imageC | Upload a local image file (path on the machine running this server) to Image Label. |
| export_annotationsB | Export an image's polygon and circle annotations as COCO JSON or YOLO, same as the web app's export. |
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 8 tools
Each tool has a clearly distinct purpose: list vs get for retrieval, update_metadata for metadata, add/replace/remove for annotation modification, upload for ingestion, and export for output. The three annotation mutation tools are explicitly differentiated by their append, replace-all, and remove-by-id behaviors.
All eight tools follow a consistent snake_case verb_noun pattern (list_images, get_image, update_image_metadata, add_annotations, replace_annotations, remove_annotations, upload_image, export_annotations). There are no mixed conventions or vague verbs.
Eight tools is well-scoped for an image labeling server, covering image retrieval, metadata updates, annotation lifecycle, upload, and export without bloat. Each tool earns its place in the core workflow.
The server covers image upload/list/get, metadata update, full annotation add/replace/remove, and export. A delete-image operation is missing, and category management is absent, but these are minor gaps for the stated annotation-focused purpose.