detection-mcp

简体中文

detection-mcp is a local STDIO Model Context Protocol server for object-detection annotation. It stores workflow state and annotations in SQLite, renders review previews in memory, and exports JSONL without modifying source images.

Status

The v1 implementation is available for review. It exposes 23 tools for datasets, categories, images, axis-aligned boxes, rotated boxes, previews, and export. The package targets Python 3.12 or newer and uses fastmcp>=3.4.7,<4.0.0, allowing compatible 3.x security updates.

Related MCP server: z_ai_vision_mcp_server_clone

Install from this repository

Install uv, then run:

uv tool install .
detection-mcp --version

For repository development:

uv sync --locked --all-groups
uv run pre-commit install --install-hooks --hook-type pre-commit --hook-type commit-msg --hook-type pre-push

Configure an MCP client

Use an installed executable and grant only the directories the task needs:

{
  "mcpServers": {
    "detection-mcp": {
      "command": "detection-mcp",
      "args": [
        "--db-path", "/var/lib/detection-mcp/annotations.db",
        "--allowed-dataset-root", "/srv/datasets",
        "--allowed-export-root", "/srv/exports"
      ]
    }
  }
}

The server uses STDIO: protocol messages go to stdout and logs go to stderr. CLI options override DETECTION_MCP_* environment variables. See configuration for all settings.

Annotation workflow

1. Register a dataset root and define categories.

2. List images by status or deterministic random order.

3. Preview an orientation-corrected image.

4. Add normalized axis-aligned or rotated boxes in atomic batches.

5. Preview the overlay and correct annotations before marking the image completed.

6. Export completed images to AutoTrain or extended JSONL.

Install the Agent Skills

The Agent Skills live only in the repository's root skills/ directory. They are not included in the Python wheel, source distribution, or container image. Install either Skill directly from GitHub with the skills CLI:

npx skills add ryan-minato/detection-mcp --skill object-detection-annotation
npx skills add ryan-minato/detection-mcp --skill detection-mcp-setup

The default installation is project-local. Add --global when the Skill should be available across projects.

Tool groups

See the complete tool reference and export format.

Development commands

just is the repository command executor:

just sync       # synchronize the locked environment
just test       # run ordinary tests
just quality-control # run CI checks without tests
just quality    # run the complete local commit gate
just hooks      # run repository hooks against tracked files
just check      # run quality and hooks

Never bypass Git hooks. Every commit requires the full quality gate and a staged secret/PII scan. See CONTRIBUTING.md, SECURITY.md, and AGENTS.md.

Containers

The production image runs as a non-root user. Dataset mounts must be read-only, while state and exports require separate writable mounts. See Docker deployment and docker-compose.example.yml.

License

Apache-2.0. See LICENSE.