| name | mcp-tools-maintainer |
|---|---|
| description | Use when changing mq-image-analyze MCP server, MCP tool schemas, tool safety, read-only behavior, or mq-mcp/mq-agent integration. |
Use this skill for MCP behavior and tool contracts.
- "add an MCP tool to the image server"
- "tighten MCP tool read-only safety"
- "fix mq-mcp integration of the image tools"
- "the MCP tool schema is wrong"
- "change a CLI flag" → use
cli-maintainer - "change the JSON result schema" → use
json-contract-maintainer - "set up a model backend" → use
model-setup-maintainer
mq_image_analyze/mcp/server.pymq_image_analyze/mcp/tools/__init__.pymq_image_analyze/mcp/schemas/__init__.pydocs/mcp-tools.mddocs/tool-safety.mddocs/integration.mdtests/test_mcp_tools.pytests/test_json_schema.py
All MCP tools are read-only by default. They inspect image files and return structured analysis. They must not write, delete, mutate, or suppress detector output.
Keep the safety classification aligned with docs/tool-safety.md.
For exhaustive mode:
- preserve every detection
- include confidence, bbox, area percent, and source model
- include content flags
- include limitations
- do not hide uncertain detections without reporting why
When changing an MCP tool:
- Update implementation.
- Update schema/docs in
docs/mcp-tools.md. - Update JSON contract docs if output changes.
- Add or update
tests/test_mcp_tools.py. - Check mq-agent and mq-mcp integration docs when relevant.
python -m pytest tests/test_mcp_tools.py tests/test_json_schema.py -q
python -m compileall mq_image_analyze/mcp -qFor full safety:
bash scripts/validate.sh