MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
fabric-lakehouse-mcpgithub.com/melisa-l/fabric-rti-mcpupdated this year
Microsoft Fabric Lakehouse MCP Server - SQL analytics tools for AI agents
pypi MIT -
iceberg-lakehousegithub.com/jpequegn/iceberg-lakehouseupdated this year
Local-first data lakehouse with Apache Iceberg storage and LLM access via MCP
-
jgi-lakehouse-mcpgithub.com/Contactashmeetsingh/jgi-lakehouse-mcpupdated this year
MCP server for searching and accessing data across JGI portals (Data Portal, GOLD, IMG/M, Mycocosm/Phytozome) and the JGI lakehouse.
NOASSERTION ★ 1 -
Lakehouse data to an AI agent: Parquet, Apache Iceberg (time travel), DuckDB SQL, and Claude over MCP with per-caller tokens, read-only guard and audit log.
MIT -
A runnable MCP server that gives AI agents governed access to Apache Iceberg tables through a semantic layer. Companion code for agenticlakehouse.com/patterns.
Apache-2.0 -
Text-to-SQL AI agent over a Bronze/Silver/Gold lakehouse: explains schemas, keys and lineage, with SQL guardrails, an MCP server and an eval set.
MIT ★ 1 -
Data pipelines aren't AI-ready until they are governed: this Databricks framework powered by Apache Spark and PySpark uses Unity Catalog and Delta Lake to serve verified, audit-ready data products through strict read-only MCP boundaries.
MIT -
@wcg-hieule/fabric-mcpupdated this year
MCP server for Microsoft Fabric Lakehouse - query, explore and analyze data
npm MIT -
@iflow-mcp/tmdaidevs-fabric-optimization-mcp-serverupdated this year
MCP Server for optimizing Microsoft Fabric items (Lakehouse, Warehouse, Eventhouse, Semantic Models)
npm MIT -
Write SQL, browse Iceberg catalogs, keep your lakehouse healthy. Self-hosted and Trino-native.
Apache-2.0 ★ 1 -
MCP server for Microsoft Fabric: workspaces, lakehouses, warehouses, table schemas, guarded read-only SQL, notebook jobs, and DAX
MIT -
Model Context Protocol (MCP) server for IBM watsonx.data - enables AI assistants to query and explore lakehouse data Resources
pypi Apache-2.0 ★ 9 -
Medallion Lakehouse (DuckDB, Parquet, dbt), ODCS v3.1 Data Contracts, and Python SDK / REST / CLI / MCP Gateway for Official Public Data Sources
MIT -
Agent-first ontologies for your lakehouse: link Delta Lake data products to OpenMetadata Ontology Studio, version them in Git, and serve them to AI agents over MCP. (Pre-alpha placeholder.)
pypi Apache-2.0 -
Microsoft Fabric enterprise BI reference build: hot and cold paths, medallion Lakehouse, semantic model, governed data agent (MCP + A2A), Purview-style governance, Terraform + Bicep. Runs offline on synthetic data.
MIT -
Creator growth intelligence lakehouse: quota-aware YouTube ingestion, DuckLake bronze, dbt marts, Dagster orchestration, a five-page Streamlit product, 10 SLO checks, and a governed MCP metric server.
MIT -
End-to-end Databricks lakehouse built with Claude Code via Spec-Driven Development: medallion, GenAI, data contracts, MCP server and CI/CD
MIT -
NL→SQL agent over a lakehouse with five deterministic control rings: AST allowlist guard, cost budget estimated before execution, role-based masking and a tamper-evident audit chain. Served over MCP.
Apache-2.0 -
Madroño — inteligencia urbana en tiempo real para Madrid: ingesta serverless (AWS Lambda+EventBridge), lakehouse medallón (S3+Glue+Athena), grafo urbano (Neo4j), modelos predictivos (LightGBM+STGNN) y un asistente conversacional (FastAPI+MCP+LLM). Trabajo de Fin de Máster.
MIT -
alchemylake-databricksgithub.com/zorost/alchemylake-databricksupdated this year
Governed, provenance-sealed creative rendering for Databricks — a Streamlit App + Unity Catalog ai_render() function that turns any governed source (Sample Lakehouse, UC, Genie, or BYO data) into infographics, reports, decks, video briefings, music, and podcasts.
Apache-2.0 ★ 118 -
alchemylake-apexgithub.com/zorost/alchemylake-apexupdated this year
Truth, made visible. AlchemyLake turns governed lakehouse data (Databricks Unity Catalog, Genie, or your own uploads) into verified, provenance-sealed deliverables: PDF reports, PowerPoint decks, infographics, video briefings, podcasts, sonified scores, deep research. MCP server (13 tools), REST API, CLI. 200 free credits.
Apache-2.0 ★ 1 -
Agentic eCommerce Governed Retail Analytics Lakehouse on Databricks: includes OLTP orders, star-schema ETL with change data capture, Unity Catalog metrics, and Genie ontology agents for analytics and fraud. MCP Server, Databricks Genie Agents, non-Databricks Agents using LangGraph and Google ADK, PySpark, FastAPI, and GitHub Actions.
Apache-2.0 -
MCP server to query and work with Microsoft Fabric warehouses, lakehouses or databases
pypi MIT ★ 3 -
fabric-mcpgithub.com/melisaluis/fabric-mcpupdated this year
This repo extends the official Microsoft Fabric RTI MCP by adding custom tools for schema discovery and direct data querying in Lakehouse environments, enabling advanced analytics and automation while maintaining compatibility with all standard RTI MCP features.
MIT -
Open-source data quality monitoring: checks across warehouses, lakehouses and object stores, triggered by ADF, Airflow and dbt, with alerting and an MCP server.
MIT -
A guide to New York City you can ask anything: an agent that answers from a live NYC lakehouse first, then city feeds and the web over MCP, with sources and a map
-
snowflake-cortex-mcp-foundry-fabric-multi-agentgithub.com/curious-bigcat/snowflake-cortex-mcp-foundry-fabric-multi-agentupdated this year
Multi-agent setup connecting Snowflake Cortex Agent (via MCP Server) with Microsoft AI Foundry and Fabric Data Agents. Foundry orchestrator routes queries to Snowflake (Cortex Analyst + Cortex Search) or Fabric (Lakehouse NL2SQL) via MCP. Includes scripts, semantic view, agent config, and end-to-end guide
-
Energy intelligence platform for solar, wind and battery storage: per-inverter soiling forecasts, fault detection and RUL, BESS warranty and revenue ledger, digital twins, an operations agent with an MCP server, Iceberg/DuckDB/dbt lakehouse. Next.js + Python.
-
An autonomous, zero-trust data governance agent leveraging the Model Context Protocol (MCP) to secure high-volume data lakehouses. Intercepts semantic query intent, maps real-time AWS IAM controls, and enforces automated PII masking via dynamic Vector RAG structures.
MIT -
iceberg-mcpgithub.com/morristai/iceberg-mcpupdated this year
MCP server for Apache Iceberg
★ 36 -
Apache Doris MCP Server
pypi Apache-2.0 ★ 359 -
Repository hosting the open source Bauplan MCP server
MIT ★ 15 -
MCP Service for GigAPI Timeseries Lake
★ 6 -
Health checks for Apache Iceberg tables: snapshots, small files, deletes, manifests. CLI + MCP server.
-
frostgithub.com/aidancorrell/frostupdated this year
Agent-first Iceberg table health tool — MCP server, CLI, and CI gate that diagnoses operational problems from metadata alone.
Apache-2.0 -
LakehouseBox for agents: the MCP connector and Agent Skills for Claude, Cowork, Codex, ChatGPT, Gemini CLI and any agent that reads skills
MIT -
263 tools for Databricks via MCP. SDK-first, covers Unity Catalog, SQL, Compute, Jobs, Serving, Vector Search, Apps, Lakebase, and more.
Apache-2.0 -
Local MCP server for validating, linting and test-running YAML data contracts with AI assistants. Powered by LakeLogic Core.
pypi Apache-2.0 -
Open source, self-hosted semantic layer and knowledge graph for AI agents. Evidence-backed definitions, human review, and reusable MCP context.
Apache-2.0 -
@einlogic/mcp-fabric-apiactive
MCP server for Microsoft Fabric REST APIs — enables data engineers and data analysts to use AI assistants beyond Copilot to build and manage Fabric components
npm AGPL-3.0 -
sas2databricksgithub.com/navintkr/sas2databricksupdated this year
sas2databricks - LLM-assisted, deterministic-first toolkit to migrate SAS analytics, transformations & reports to Databricks (PySpark, Spark SQL, DLT, Workflows). CLI + MCP + Copilot agent with model picker (Opus 4.8/Codex/Auto).
MIT -
MCP server that stops an AI agent's Trino or Pinot query before it stalls your shared cluster: priced from the engine's own plan, refused with a fix the agent can act on
pypi Apache-2.0 ★ 1 -
apache-polaris-iceberg-ai-mcpgithub.com/sankeerthnagapuri/apache-polaris-iceberg-ai-mcpupdated this year
Model Context Protocol (MCP) server for Apache Polaris. Enables AI agents and LLMs to interact with Polaris Catalog Management, audit data governance and access control (RBAC) policies, and perform Iceberg table inspections using PyIceberg.
MIT ★ 1 -
Read-only MCP server for Trino: each query runs as the user who asked, and Trino's access control decides what they see. Nine tools, writes refused on the SQL tree, bounded SQL, rows, bytes and time. Any MCP host, any model.
pypi Apache-2.0 ★ 7