Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Mini Data Engine Runtime Copilot

OCI · GHCR.IO/KROQ86/DATA-ENGINEERING-RUNTIME-LAB:0.1.12 · SCANNED SEP 20

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

0 this week 46 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency45
Schema Quality & AI Usability53
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 2838 tokens (~60/item across 47 items; 47 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "run_e2e_flow" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 47 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

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

How do I install the Mini Data Engine Runtime Copilot MCP server?

Mini Data Engine Runtime Copilot runs locally as a container image, launched with docker run --rm -i ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12

# add to Claude Code
claude mcp add kroq86-mini-data-engine -- docker run --rm -i ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12
// .cursor/mcp.json
{
  "mcpServers": {
    "kroq86-mini-data-engine": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "kroq86-mini-data-engine": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"
      ]
    }
  }
}
# add to Codex CLI
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/config.yaml
mcp_servers:
  kroq86-mini-data-engine:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "kroq86-mini-data-engine": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12"
      ]
    }
  }
}
// mcp.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 we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 19 Sept 26 +1
    • Security disclosure: fail → unverified functional
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 −3
    • Stability: pass → 0.83 functional
  • 15 Sept 26 +1
    • Stability: 0.97 → pass security
  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Sept 26 −3
    • Stability: pass → 0.80 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed oci/ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 47 exposed · ~2,838 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
benchmark_calls ~59

Benchmark MCP operations with SLO-style summary metrics.

NameTypeReqDescription
iterationsinteger
max_p95_msnumber
min_success_ratenumber
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

capture_roi_baseline ~59

Capture baseline KPI snapshot for ROI Phase 0.

NameTypeReqDescription
benchmark_iterationsinteger
output_pathstring
root_dirstring
scenario_iterationsinteger
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

create_index ~30

Create customer index for engine table.

NameTypeReqDescription
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

decision_gate ~85

Evaluate migration triggers and return pass/fail gate.

NameTypeReqDescription
baseline_pathstring
consecutive_regressions_requiredinteger
drift_counter_pathstring
need_rust_portfolioboolean
regression_threshold_pctnumber
trace_db_pathstring
volume_threshold_per_dayinteger

Structured output declared, but exposes no named fields.

No examples provided.

demo_explain_concurrency_failure_storm ~56

Run a traced concurrency conflict plus failure-storm scenario.

NameTypeReqDescription
root_dirstring
tablestring
trace_db_pathstring
workersinteger

Structured output declared, but exposes no named fields.

No examples provided.

demo_explain_idempotency_conflict ~36

Run a traced idempotency-conflict flow through WriteCore.

NameTypeReqDescription
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

demo_explain_run ~54

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

NameTypeReqDescription
customer_idinteger
root_dirstring
tablestring
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

demo_explain_run_failure ~48

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

NameTypeReqDescription
root_dirstring
tablestring
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

demo_explain_semantic_failure ~57

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

NameTypeReqDescription
customer_idinteger
root_dirstring
tablestring
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

explain_customer ~44

Run EXPLAIN ANALYZE style output by customer filter.

NameTypeReqDescription
customer_idinteger
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

explain_regression_suite ~55

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

NameTypeReqDescription
benchmark_iterationsinteger
root_prefixstring
scenario_iterationsinteger
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

explain_run ~46

Explain one recorded run_id from the local trace store.

NameTypeReqDescription
max_timeline_eventsinteger
run_idstringyes
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

health_check ~33

Run a quick MCP smoke flow and summarize status.

NameTypeReqDescription
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

init_engine ~28

Initialize persistent engine storage.

NameTypeReqDescription
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

insert_row ~54

Insert one row into the persistent engine.

NameTypeReqDescription
amountinteger
customer_idinteger
order_idinteger
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

memory_search ~101

Search memory entries by semantic similarity and metadata filters.

NameTypeReqDescription
end_time_utcstring
min_scorenumber
query_textstringyes
scenario_idstring
start_time_utcstring
statusstring
tagsstring
tool_namestring
top_kinteger
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

memory_upsert ~122

Upsert one operational memory entry for semantic recall.

NameTypeReqDescription
actual_effectsstring
correlation_idstring
decision_reasonstring
error_textstring
memory_idstring
metadata_jsonstring
run_idstringyes
scenario_idstring
statusstring
summarystringyes
tagsstring
tool_namestring
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

project_append_event ~76

Append a generic project event to the local event log.

NameTypeReqDescription
decision_reasonstring
entity_idstring
entity_typestring
event_typestring
payload_jsonstring
root_dirstring
run_idstring

Structured output declared, but exposes no named fields.

No examples provided.

project_capabilities ~17

Return declared runtime capabilities and contract coverage.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

project_capture_baseline ~60

Capture a baseline snapshot and return a unified verdict envelope.

NameTypeReqDescription
benchmark_iterationsinteger
output_pathstring
root_dirstring
scenario_iterationsinteger
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

project_compare_baseline ~92

Compare current benchmark/scenario results against a stored baseline.

NameTypeReqDescription
baseline_pathstring
benchmark_iterationsinteger
benchmark_regression_pctnumber
e2e_regression_pctnumber
root_dirstring
scenario_iterationsinteger
scenario_regression_pctnumber
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

project_delete_entity ~51

Delete a declared entity from the generic state store.

NameTypeReqDescription
dry_runboolean
entity_idstring
entity_typestring
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

project_explain_run ~49

Read one run explanation through the generic project explain entrypoint.

NameTypeReqDescription
max_timeline_eventsinteger
run_idstringyes
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

project_export_state ~50

Export generic project state as a JSON snapshot.

NameTypeReqDescription
entity_typestring
include_eventsboolean
output_pathstring
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

project_get_defaults ~22

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

project_get_entity ~42

Load one declared project entity by identity key.

NameTypeReqDescription
entity_idstring
entity_typestring
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

project_ingest_trace ~134

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

NameTypeReqDescription
actual_effectsstring
attemptinteger
correlation_idstring
decision_reasonstring
error_textstring
retry_classificationstring
run_idstringyes
scenario_idstring
source_kindstring
source_pathstring
statusstringyes
summarystringyes
tool_namestringyes
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

project_list_entities ~42

List declared project entities from the generic state store.

NameTypeReqDescription
entity_typestring
limitinteger
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

project_list_heuristics ~21

List declared heuristic profiles available for generic project analysis.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

project_manifest ~20

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

project_run_heuristic ~82

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

NameTypeReqDescription
heuristic_namestringyes
max_examplesinteger
persistboolean
root_dirstring
run_idstring
source_kindstring
source_pathstringyes

Structured output declared, but exposes no named fields.

No examples provided.

project_run_regression ~55

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

NameTypeReqDescription
benchmark_iterationsinteger
root_prefixstring
scenario_iterationsinteger
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

project_tool_catalog ~31

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

NameTypeReqDescription
groupstring

Structured output declared, but exposes no named fields.

No examples provided.

project_upsert_entity ~69

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

NameTypeReqDescription
dry_runboolean
entity_idstring
entity_typestring
mergeboolean
payload_jsonstring
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

record_tool_trace ~124

Append one MCP tool trace record to local trace store.

NameTypeReqDescription
actual_effectsstring
attemptinteger
correlation_idstring
decision_reasonstring
elapsed_msnumber
error_textstring
retry_classificationstring
run_idstringyes
scenario_idstring
statusstringyes
summarystringyes
tool_namestringyes
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

refresh_docs_path ~90

Incrementally ingest project docs, code, and config files.

NameTypeReqDescription
exclude_dir_namesstring
exclude_path_partsstring
include_extensionsstring
max_file_bytesinteger
refresh_state_pathstring
scenario_idstring
source_dirstring
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

refresh_trace_path ~55

Incrementally ingest new lines from source path into trace store.

NameTypeReqDescription
refresh_state_pathstring
scenario_idstring
source_pathstringyes
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

reindex_project ~34

Re-index this project dataset (engine_cli index).

NameTypeReqDescription
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

report_drift_bug ~35

Increment and persist split-logic drift bug counter.

NameTypeReqDescription
counter_pathstring
notestring

Structured output declared, but exposes no named fields.

No examples provided.

run_e2e_flow ~36

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

NameTypeReqDescription
root_dirstring

Structured output declared, but exposes no named fields.

No examples provided.

scenario_load_test ~88

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

NameTypeReqDescription
iterationsinteger
max_e2e_p95_msnumber
max_overall_p95_msnumber
min_success_ratenumber
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

schema_evaluate_full_tool ~112

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

NameTypeReqDescription
artifacts_dirstring
ddl_textstring
query_profile_namesstring
query_profiles_jsonstring
root_dirstring
schema_entity_idstring
schema_pathstring
seed_sql_jsonstring

Structured output declared, but exposes no named fields.

No examples provided.

schema_evaluate_tool ~77

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.

NameTypeReqDescription
artifacts_dirstring
query_profile_namesstring
root_dirstring
schema_entity_idstring

Structured output declared, but exposes no named fields.

No examples provided.

schema_explain_tool ~94

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.

NameTypeReqDescription
artifacts_dirstring
query_profiles_jsonstring
root_dirstring
schema_entity_idstring
seed_sql_jsonstring

Structured output declared, but exposes no named fields.

No examples provided.

schema_load_tool ~66

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

NameTypeReqDescription
ddl_textstring
root_dirstring
schema_entity_idstring
schema_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

similar_incidents ~92

Find semantically similar historical incidents.

NameTypeReqDescription
end_time_utcstring
min_scorenumber
query_textstringyes
scenario_idstring
start_time_utcstring
statusstring
tool_namestring
top_kinteger
trace_db_pathstring

Structured output declared, but exposes no named fields.

No examples provided.

upsert_row ~55

Upsert one row by order_id.

NameTypeReqDescription
amountinteger
customer_idinteger
order_idinteger
root_dirstring
tablestring

Structured output declared, but exposes no named fields.

No examples provided.

Common questions

What is the Mini Data Engine Runtime Copilot MCP server?

Mini Data Engine Runtime Copilot is an MCP server listed in the public MCP registry as io.github.kroq86/mini-data-engine. MCP runtime copilot for health checks, regressions, explainability, and operational memory. This page covers its container image (ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12).

Is the Mini Data Engine Runtime Copilot MCP server safe to use?

Mini Data Engine Runtime Copilot scores 46 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Mini Data Engine Runtime Copilot MCP server expose?

Mini Data Engine Runtime Copilot exposes 47 tools: init_engine, insert_row, upsert_row, create_index, explain_customer, and 42 more. Their descriptions and schemas cost roughly 2,838 tokens of context every time the server is loaded.

Is the Mini Data Engine Runtime Copilot MCP server still maintained?

Mini Data Engine Runtime Copilot is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Mini Data Engine Runtime Copilot MCP server under?

Mini Data Engine Runtime Copilot declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.