# Mini Data Engine Runtime Copilot (oci · ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12)

MCP runtime copilot for health checks, regressions, explainability, and operational memory.

- Trust score: 32/100 (low)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- oci · `ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12`: 32/100 (this document), [markdown](https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12.md), [page](https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 139 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 37/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 2838 tokens (~60/item across 47 items; 47 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add kroq86-mini-data-engine -- docker run --rm -i ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12
```

### Codex

```bash
codex mcp add kroq86-mini-data-engine -- docker run --rm -i ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "kroq86-mini-data-engine": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  kroq86-mini-data-engine:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"]
```

### Other

```json
{
  "mcpServers": {
    "kroq86-mini-data-engine": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 32, +3)

- [functional improvement] Stability: unverified → 0.20

### 2026-08-01 (score 29, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 31, +20)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: poor
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 0

### 2026-07-26 (score 11)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (47)

### `init_engine` (~28 tokens)

Initialize persistent engine storage.

Input parameters:

- `root_dir` (string)
- `table` (string)

### `insert_row` (~54 tokens)

Insert one row into the persistent engine.

Input parameters:

- `amount` (integer)
- `customer_id` (integer)
- `order_id` (integer)
- `root_dir` (string)
- `table` (string)

### `upsert_row` (~55 tokens)

Upsert one row by order_id.

Input parameters:

- `amount` (integer)
- `customer_id` (integer)
- `order_id` (integer)
- `root_dir` (string)
- `table` (string)

### `create_index` (~30 tokens)

Create customer index for engine table.

Input parameters:

- `root_dir` (string)
- `table` (string)

### `explain_customer` (~44 tokens)

Run EXPLAIN ANALYZE style output by customer filter.

Input parameters:

- `customer_id` (integer)
- `root_dir` (string)
- `table` (string)

### `reindex_project` (~34 tokens)

Re-index this project dataset (engine_cli index).

Input parameters:

- `root_dir` (string)
- `table` (string)

### `run_e2e_flow` (~36 tokens)

Execute full MiniPG + MiniDatabricks + DuckDB end-to-end flow.

Input parameters:

- `root_dir` (string)

### `explain_run` (~46 tokens)

Explain one recorded run_id from the local trace store.

Input parameters:

- `max_timeline_events` (integer)
- `run_id` (string, required)
- `trace_db_path` (string)

### `demo_explain_run` (~54 tokens)

Run a traced demo flow, then explain the run immediately.

Input parameters:

- `customer_id` (integer)
- `root_dir` (string)
- `table` (string)
- `trace_db_path` (string)

### `demo_explain_run_failure` (~48 tokens)

Run a traced failing flow, then explain the failed run immediately.

Input parameters:

- `root_dir` (string)
- `table` (string)
- `trace_db_path` (string)

### `demo_explain_semantic_failure` (~57 tokens)

Run a traced semantic-corruption flow and explain the failed validation.

Input parameters:

- `customer_id` (integer)
- `root_dir` (string)
- `table` (string)
- `trace_db_path` (string)

### `demo_explain_idempotency_conflict` (~36 tokens)

Run a traced idempotency-conflict flow through WriteCore.

Input parameters:

- `trace_db_path` (string)

### `demo_explain_concurrency_failure_storm` (~56 tokens)

Run a traced concurrency conflict plus failure-storm scenario.

Input parameters:

- `root_dir` (string)
- `table` (string)
- `trace_db_path` (string)
- `workers` (integer)

### `explain_regression_suite` (~55 tokens)

Run regression checks and return explain output for each traced run.

Input parameters:

- `benchmark_iterations` (integer)
- `root_prefix` (string)
- `scenario_iterations` (integer)
- `trace_db_path` (string)

### `record_tool_trace` (~124 tokens)

Append one MCP tool trace record to local trace store.

Input parameters:

- `actual_effects` (string)
- `attempt` (integer)
- `correlation_id` (string)
- `decision_reason` (string)
- `elapsed_ms` (number)
- `error_text` (string)
- `retry_classification` (string)
- `run_id` (string, required)
- `scenario_id` (string)
- `status` (string, required)
- `summary` (string, required)
- `tool_name` (string, required)
- `trace_db_path` (string)

### `similar_incidents` (~92 tokens)

Find semantically similar historical incidents.

Input parameters:

- `end_time_utc` (string)
- `min_score` (number)
- `query_text` (string, required)
- `scenario_id` (string)
- `start_time_utc` (string)
- `status` (string)
- `tool_name` (string)
- `top_k` (integer)
- `trace_db_path` (string)

### `refresh_trace_path` (~55 tokens)

Incrementally ingest new lines from source path into trace store.

Input parameters:

- `refresh_state_path` (string)
- `scenario_id` (string)
- `source_path` (string, required)
- `trace_db_path` (string)

### `refresh_docs_path` (~90 tokens)

Incrementally ingest project docs, code, and config files.

Input parameters:

- `exclude_dir_names` (string)
- `exclude_path_parts` (string)
- `include_extensions` (string)
- `max_file_bytes` (integer)
- `refresh_state_path` (string)
- `scenario_id` (string)
- `source_dir` (string)
- `trace_db_path` (string)

### `memory_upsert` (~122 tokens)

Upsert one operational memory entry for semantic recall.

Input parameters:

- `actual_effects` (string)
- `correlation_id` (string)
- `decision_reason` (string)
- `error_text` (string)
- `memory_id` (string)
- `metadata_json` (string)
- `run_id` (string, required)
- `scenario_id` (string)
- `status` (string)
- `summary` (string, required)
- `tags` (string)
- `tool_name` (string)
- `trace_db_path` (string)

### `memory_search` (~101 tokens)

Search memory entries by semantic similarity and metadata filters.

Input parameters:

- `end_time_utc` (string)
- `min_score` (number)
- `query_text` (string, required)
- `scenario_id` (string)
- `start_time_utc` (string)
- `status` (string)
- `tags` (string)
- `tool_name` (string)
- `top_k` (integer)
- `trace_db_path` (string)

### `health_check` (~33 tokens)

Run a quick MCP smoke flow and summarize status.

Input parameters:

- `root_dir` (string)
- `table` (string)

### `benchmark_calls` (~59 tokens)

Benchmark MCP operations with SLO-style summary metrics.

Input parameters:

- `iterations` (integer)
- `max_p95_ms` (number)
- `min_success_rate` (number)
- `root_dir` (string)
- `table` (string)

### `scenario_load_test` (~88 tokens)

Mixed workload load test:
    insert/upsert/explain/reindex/e2e and summary metrics.

Input parameters:

- `iterations` (integer)
- `max_e2e_p95_ms` (number)
- `max_overall_p95_ms` (number)
- `min_success_rate` (number)
- `root_dir` (string)
- `table` (string)

### `capture_roi_baseline` (~59 tokens)

Capture baseline KPI snapshot for ROI Phase 0.

Input parameters:

- `benchmark_iterations` (integer)
- `output_path` (string)
- `root_dir` (string)
- `scenario_iterations` (integer)
- `table` (string)

### `report_drift_bug` (~35 tokens)

Increment and persist split-logic drift bug counter.

Input parameters:

- `counter_path` (string)
- `note` (string)

### `decision_gate` (~85 tokens)

Evaluate migration triggers and return pass/fail gate.

Input parameters:

- `baseline_path` (string)
- `consecutive_regressions_required` (integer)
- `drift_counter_path` (string)
- `need_rust_portfolio` (boolean)
- `regression_threshold_pct` (number)
- `trace_db_path` (string)
- `volume_threshold_per_day` (integer)

### `project_manifest` (~20 tokens)

Describe project state roots, schemas, and supported regression primitives.

### `project_capabilities` (~17 tokens)

Return declared runtime capabilities and contract coverage.

### `project_tool_catalog` (~31 tokens)

Return the full MCP tool catalog with groups, entrypoints, and summaries.

Input parameters:

- `group` (string)

### `project_get_defaults` (~22 tokens)

Return default workspace, paths, runtime mode, and project metadata.

### `project_run_regression` (~55 tokens)

Run the explain-first regression bundle and return a unified verdict.

Input parameters:

- `benchmark_iterations` (integer)
- `root_prefix` (string)
- `scenario_iterations` (integer)
- `trace_db_path` (string)

### `project_capture_baseline` (~60 tokens)

Capture a baseline snapshot and return a unified verdict envelope.

Input parameters:

- `benchmark_iterations` (integer)
- `output_path` (string)
- `root_dir` (string)
- `scenario_iterations` (integer)
- `table` (string)

### `project_compare_baseline` (~92 tokens)

Compare current benchmark/scenario results against a stored baseline.

Input parameters:

- `baseline_path` (string)
- `benchmark_iterations` (integer)
- `benchmark_regression_pct` (number)
- `e2e_regression_pct` (number)
- `root_dir` (string)
- `scenario_iterations` (integer)
- `scenario_regression_pct` (number)
- `table` (string)

### `project_list_entities` (~42 tokens)

List declared project entities from the generic state store.

Input parameters:

- `entity_type` (string)
- `limit` (integer)
- `root_dir` (string)

### `project_get_entity` (~42 tokens)

Load one declared project entity by identity key.

Input parameters:

- `entity_id` (string)
- `entity_type` (string)
- `root_dir` (string)

### `project_upsert_entity` (~69 tokens)

Create or update a declared entity in the generic state store.

Input parameters:

- `dry_run` (boolean)
- `entity_id` (string)
- `entity_type` (string)
- `merge` (boolean)
- `payload_json` (string)
- `root_dir` (string)

### `project_delete_entity` (~51 tokens)

Delete a declared entity from the generic state store.

Input parameters:

- `dry_run` (boolean)
- `entity_id` (string)
- `entity_type` (string)
- `root_dir` (string)

### `project_append_event` (~76 tokens)

Append a generic project event to the local event log.

Input parameters:

- `decision_reason` (string)
- `entity_id` (string)
- `entity_type` (string)
- `event_type` (string)
- `payload_json` (string)
- `root_dir` (string)
- `run_id` (string)

### `project_ingest_trace` (~134 tokens)

Append one normalized trace record through the generic project ingest path.

Input parameters:

- `actual_effects` (string)
- `attempt` (integer)
- `correlation_id` (string)
- `decision_reason` (string)
- `error_text` (string)
- `retry_classification` (string)
- `run_id` (string, required)
- `scenario_id` (string)
- `source_kind` (string)
- `source_path` (string)
- `status` (string, required)
- `summary` (string, required)
- `tool_name` (string, required)
- `trace_db_path` (string)

### `project_explain_run` (~49 tokens)

Read one run explanation through the generic project explain entrypoint.

Input parameters:

- `max_timeline_events` (integer)
- `run_id` (string, required)
- `trace_db_path` (string)

### `project_export_state` (~50 tokens)

Export generic project state as a JSON snapshot.

Input parameters:

- `entity_type` (string)
- `include_events` (boolean)
- `output_path` (string)
- `root_dir` (string)

### `project_list_heuristics` (~21 tokens)

List declared heuristic profiles available for generic project analysis.

### `project_run_heuristic` (~82 tokens)

Run one declared heuristic profile over a source and persist the analysis through project state.

Input parameters:

- `heuristic_name` (string, required)
- `max_examples` (integer)
- `persist` (boolean)
- `root_dir` (string)
- `run_id` (string)
- `source_kind` (string)
- `source_path` (string, required)

### `schema_load_tool` (~66 tokens)

Ingest DDL from file or raw text, validate with DuckDB, store metadata in project state (schemas/).

Input parameters:

- `ddl_text` (string)
- `root_dir` (string)
- `schema_entity_id` (string)
- `schema_path` (string)

### `schema_explain_tool` (~94 tokens)

Run EXPLAIN for each profile in query_profiles_json (JSON: name -> SQL). Optional seed_sql_json (JSON array of SQL) runs before EXPLAIN. Writes explain_<name>.txt.

Input parameters:

- `artifacts_dir` (string)
- `query_profiles_json` (string)
- `root_dir` (string)
- `schema_entity_id` (string)
- `seed_sql_json` (string)

### `schema_evaluate_tool` (~77 tokens)

Build verdict from schema metadata and EXPLAIN outputs; write evaluation_report.json and verdict.md. If query_profile_names empty, discovers explain_*.txt in artifacts.

Input parameters:

- `artifacts_dir` (string)
- `query_profile_names` (string)
- `root_dir` (string)
- `schema_entity_id` (string)

### `schema_evaluate_full_tool` (~112 tokens)

One-shot: load schema → run EXPLAIN (from query_profiles_json/seed_sql_json) → evaluate. Generic: you supply queries and optional seed SQL.

Input parameters:

- `artifacts_dir` (string)
- `ddl_text` (string)
- `query_profile_names` (string)
- `query_profiles_json` (string)
- `root_dir` (string)
- `schema_entity_id` (string)
- `schema_path` (string)
- `seed_sql_json` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12#diagnostics

## Score history

- 2026-08-03: 32
- 2026-08-02: 32
- 2026-08-01: 29
- 2026-07-31: 31
- 2026-07-29: 31
- 2026-07-28: 31
- 2026-07-27: 31
- 2026-07-26: 11

## Links

- Repository: https://github.com/kroq86/data-engineering-runtime-lab
- Changelog RSS feed: https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12/changelog.json
- HTML version of this page: https://verifymcp.io/servers/kroq86-mini-data-engine/ghcr-io-kroq86-data-engineering-runtime-lab-0-1-12