Menu
Routine read-only debugging for the image-scoring Python backend via MCP—is-be-mcp search+dispatch, scoring/tagging failures, job errors, Postgres questions, DB integrity, and config sanity.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.
Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.
Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.
Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.
Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.
Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.
| name | imgscore-mcp-debug |
| description | Routine read-only debugging for the image-scoring Python backend via MCP—is-be-mcp search+dispatch, scoring/tagging failures, job errors, Postgres questions, DB integrity, and config sanity. |
Read-only triage for image-scoring-backend using MCP. Do not mutate DB/config unless the user explicitly asks.
is-be-mcp: search(query) → dispatch(action_id, arguments). Contract: MCP_SEARCH_DISPATCH.md.
| Key | Use |
|---|---|
is-be-mcp | Default — search, dispatch |
is-be-live | Legacy raw tools via MCP_SSE_PROFILE=full; execute_code when enabled |
Gallery sibling: is-ui-local gallery_status, is-ui-api api_*.
search("scoring errors") → dispatch("diagnostics.get_error_summary", {})dispatch("diagnostics.check_database_health", {}), dispatch("diagnostics.validate_config", {})dispatch("jobs.get_failed_images", {"limit": 20}), dispatch("jobs.get_run_diagnostics", {"run_id": N}) when run id knowndispatch("logs.search_logs", {"pattern": "error|failed"}), dispatch("logs.read_debug_log", {"lines": 100})On is-be-live SSE: execute_code, run_processing_job, set_config_value, prune_missing_files, …
When is-be-mcp fails live discovery, probe the WebUI REST API directly (prefer curl.exe + file bodies on Windows — see agent-data-config).
Confirmed read endpoints:
| Method | Path | Use |
|---|---|---|
| GET | /api/health | Liveness (200) — not /api/status/health (404) |
| GET | /api/runs/drive/status | Auto-drive enabled / last tick / outstanding |
| GET | /api/jobs/queue | queue_size, active_runner |
| GET | /api/jobs/recent?limit=N | Recent job status |
| GET | /api/runs/folder-buckets?limit=N&offset=0 | Planner buckets / phase progress |
Writes (need user intent): POST /api/runs/drive/start, POST /api/runs/drive/stop.
Do not guess these paths:
/api/status/health → 404/api/runs/drive/diagnostics → matches /api/runs/{run_id}/diagnostics and fails int_parsing on run_idQueue-cleared condition (for "process the queue until done"):
folder-buckets total == 0 with no awaiting_* or in_flight bucketsjobs/queue queue_size == 0 and active_runner == nullCompleted scoring / culling / keywords jobs alone are not enough — folders can remain at awaiting_bird_species afterward. Full-pipeline target_phases include bird_species (indexing → metadata → scoring → culling → keywords → bird_species).