Mini Data Engine Runtime Copilot
MCP runtime copilot for health checks, regressions, explainability, and operational memory.
Connector by kroq86 · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/kroq86-mini-data-engine
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 16 read · 13 write · 1 delete · 17 not yet classified
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Docker image
Tools by what they do 47
Read from the source code; the running server may list different tools.
Read 16 · Look things up without changing anything.
capture_roi_baselinedecision_gateexplain_runmemory_searchproject_capabilitiesproject_capture_baselineproject_compare_baselineproject_explain_runproject_get_defaultsproject_get_entityproject_list_entitiesproject_list_heuristics
Show 4 more tools
project_manifestproject_tool_catalogschema_evaluate_full_toolsimilar_incidents
Write 13 · Create, change, send or run things.
benchmark_callscreate_indexinsert_rowmemory_upsertproject_append_eventproject_ingest_traceproject_run_heuristicproject_run_regressionproject_upsert_entityrecord_tool_tracereport_drift_bugrun_e2e_flow
Show 1 more tools
upsert_row
Delete 1 · Delete, drop, revoke or wipe things.
project_delete_entity
Not yet classified 17 · We could not tell from the name and description.
demo_explain_concurrency_failure_stormdemo_explain_idempotency_conflictdemo_explain_rundemo_explain_run_failuredemo_explain_semantic_failureexplain_customerexplain_regression_suitehealth_checkinit_engineproject_export_staterefresh_docs_pathrefresh_trace_path
Show 5 more tools
reindex_projectscenario_load_testschema_evaluate_toolschema_explain_toolschema_load_tool
Files it touches
- Any path the agent passes to its tools
Tools (47)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
benchmark_callsBenchmark MCP operations with SLO-style summary metrics.
capture_roi_baselineCapture baseline KPI snapshot for ROI Phase 0.
create_indexCreate customer index for engine table.
decision_gateEvaluate migration triggers and return pass/fail gate.
demo_explain_concurrency_failure_stormRun a traced concurrency conflict plus failure-storm scenario.
demo_explain_idempotency_conflictRun a traced idempotency-conflict flow through WriteCore.
demo_explain_runRun a traced demo flow, then explain the run immediately.
demo_explain_run_failureRun a traced failing flow, then explain the failed run immediately.
demo_explain_semantic_failureRun a traced semantic-corruption flow and explain the failed validation.
explain_customerRun EXPLAIN ANALYZE style output by customer filter.
explain_regression_suiteRun regression checks and return explain output for each traced run.
explain_runExplain one recorded run_id from the local trace store.
health_checkRun a quick MCP smoke flow and summarize status.
init_engineInitialize persistent engine storage.
insert_rowInsert one row into the persistent engine.
Show 32 more tools
memory_searchSearch memory entries by semantic similarity and metadata filters.
memory_upsertUpsert one operational memory entry for semantic recall.
project_append_eventAppend a generic project event to the local event log.
project_capabilitiesReturn declared runtime capabilities and contract coverage.
project_capture_baselineCapture a baseline snapshot and return a unified verdict envelope.
project_compare_baselineCompare current benchmark/scenario results against a stored baseline.
project_delete_entityDelete a declared entity from the generic state store.
project_explain_runRead one run explanation through the generic project explain entrypoint.
project_export_stateExport generic project state as a JSON snapshot.
project_get_defaultsReturn default workspace, paths, runtime mode, and project metadata.
project_get_entityLoad one declared project entity by identity key.
project_ingest_traceAppend one normalized trace record through the generic project ingest path.
project_list_entitiesList declared project entities from the generic state store.
project_list_heuristicsList declared heuristic profiles available for generic project analysis.
project_manifestDescribe project state roots, schemas, and supported regression primitives.
project_run_heuristicRun one declared heuristic profile over a source and persist the analysis through project state.
project_run_regressionRun the explain-first regression bundle and return a unified verdict.
project_tool_catalogReturn the full MCP tool catalog with groups, entrypoints, and summaries.
project_upsert_entityCreate or update a declared entity in the generic state store.
record_tool_traceAppend one MCP tool trace record to local trace store.
refresh_docs_pathIncrementally ingest project docs, code, and config files.
refresh_trace_pathIncrementally ingest new lines from source path into trace store.
reindex_projectRe-index this project dataset (engine_cli index).
report_drift_bugIncrement and persist split-logic drift bug counter.
run_e2e_flowExecute full MiniPG + MiniDatabricks + DuckDB end-to-end flow.
scenario_load_testMixed workload load test: insert/upsert/explain/reindex/e2e and summary metrics.
schema_evaluate_full_toolOne-shot: load schema → run EXPLAIN (from query_profiles_json/seed_sql_json) → evaluate. Generic: you supply queries and optional seed SQL.
schema_evaluate_toolBuild verdict from schema metadata and EXPLAIN outputs; write evaluation_report.json and verdict.md. If query_profile_names empty, discovers explain_*.txt in artifacts.
schema_explain_toolRun 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.
schema_load_toolIngest DDL from file or raw text, validate with DuckDB, store metadata in project state (schemas/).
similar_incidentsFind semantically similar historical incidents.
upsert_rowUpsert one row by order_id.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- May 31, 2026 (5 months ago)
- Last release
- May 31, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Registry name
io.github.kroq86/mini-data-engine- Version
- 0.1.12
- Auth
- No auth
- Packages
- oci
ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12 - License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from kroq86
Cite this page
Mini Data Engine Runtime Copilot MCP server. Agent Mart. https://agentmart.dev/connectors/kroq86-mini-data-engine (last updated 2026-10-24)