Mini Data Engine Runtime Copilot
A runtime diagnostics layer for local data engineering labs that wraps PostgreSQL-like and Databricks-like toy implementations with MCP tooling. Exposes 47 operations including explain_run for traced execution timelines, project_run_regression for full test suites with explainability, health_check and benchmark_calls for SLO tracking, and memory_search for incident retrieval. Built for teams running onboarding workshops or teaching storage internals who want runtime operations accessible through structured tooling instead of shell scripts. The explain layer treats both successful runs and controlled failure scenarios as first-class traced events, so you can inspect idempotency conflicts or concurrency storms the same way you'd review a prod incident.
- tools
- 47
- transport
- STDIO
- last updated
- Mar 16, 2026
Tools
47 toolsPublic tool metadata for what this MCP can expose to an agent.
init_engineEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
insert_rowEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
upsert_rowEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
create_indexEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
explain_customerEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
reindex_projectEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
run_e2e_flowEngine state and runtime tool.
Engine state and runtime tool.
No parameter schema in public metadata yet.
explain_runExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
demo_explain_runExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
demo_explain_run_failureExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
demo_explain_semantic_failureExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
demo_explain_idempotency_conflictExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
demo_explain_concurrency_failure_stormExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
explain_regression_suiteExplainability and demos tool.
Explainability and demos tool.
No parameter schema in public metadata yet.
record_tool_traceTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
similar_incidentsTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
refresh_trace_pathTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
refresh_docs_pathTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
memory_upsertTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
memory_searchTrace and retrieval tool.
Trace and retrieval tool.
No parameter schema in public metadata yet.
health_checkSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
benchmark_callsSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
scenario_load_testSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
capture_roi_baselineSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
report_drift_bugSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
decision_gateSLO and ROI tool.
SLO and ROI tool.
No parameter schema in public metadata yet.
schema_load_toolSchema evaluation tool.
Schema evaluation tool.
No parameter schema in public metadata yet.
schema_explain_toolSchema evaluation tool.
Schema evaluation tool.
No parameter schema in public metadata yet.
schema_evaluate_toolSchema evaluation tool.
Schema evaluation tool.
No parameter schema in public metadata yet.
schema_evaluate_full_toolSchema evaluation tool.
Schema evaluation tool.
No parameter schema in public metadata yet.
project_manifestProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_capabilitiesProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_tool_catalogProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_get_defaultsProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_run_regressionProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_capture_baselineProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_compare_baselineProject contract and regression tool.
Project contract and regression tool.
No parameter schema in public metadata yet.
project_list_entitiesGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_get_entityGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_upsert_entityGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_delete_entityGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_append_eventGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_ingest_traceGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_explain_runGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_export_stateGeneric project state tool.
Generic project state tool.
No parameter schema in public metadata yet.
project_list_heuristicsGeneric heuristics tool.
Generic heuristics tool.
No parameter schema in public metadata yet.
project_run_heuristicGeneric heuristics tool.
Generic heuristics tool.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Interactive Data Systems Lab
Runnable Python and Rust data-system internals with an MCP-native runtime copilot layer.
This repository combines two things:
- a local-first engineering lab for PostgreSQL-like and Databricks-like internals,
- a Runtime Copilot MCP surface for diagnostics, explainability, regression checks, and operational memory.
Core capabilities
- Storage and planner internals: heap tables, B-tree indexing, selectivity, and plan choice.
- Persistence and replay: WAL/checkpoint style flows and deterministic state transitions.
- Workflow and write-path modeling: event-first architecture, idempotency, retry semantics.
- Explainable runtime operations: traced runs, failure summaries, regression verdicts, baseline compare.
- MCP access: machine-usable operational interface instead of ad hoc shell scripts.
Who this is for
- Data engineers learning warehouse and query-engine internals.
- Platform and infrastructure engineers teaching storage and execution fundamentals.
- Teams building onboarding labs, workshops, and demo environments.
Quick start
Requirements:
- Python 3.10+ (tested with Python 3.14)
Setup:
Details
- Repository
- github.com/kroq86/data-engineering-runtime-lab
- Categories
- AI & LLM Tools, Data & Analytics
- Package
ghcr.io/kroq86/data-engineering-runtime-lab:0.1.12- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Fixflowmagneticdogson/fixflow-mcpCollective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.0stars
A2a Bridgemdfifty50-boop/a2a-bridge-mcpAgent-to-agent communication bridge for multi-agent systems0stars
SwarmHaulio.github.mighty840/swarmhaulMulti-agent coordination protocol on Solana. Swarm formation, on-chain settlement, 14 MCP tools.0stars
datamcp — Hosted Model Context Protocol for Databases, APIs, and Agent Memoryio.github.mironovisa/datamcpPostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.0stars
N3MemoryCore Lite (Working Memory)neuralnexusnote/n3mcmcp-liteEphemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.0stars
PathCourse Health (PCH)pathcourse-health/pch-mcp-serverCheaper LLM inference, USDC agent payments via x402, agent identity / reputation lookup.0stars