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.
-
jupyter-lineage-mcpgithub.com/aakashkh/jupyter-lineage-mcpupdated this year
MCP server for static data lineage in Jupyter notebooks and Python ETL jobs
MIT -
A personal PoC exploring GraphRAG design patterns: combining LangChain orchestration, Neo4j knowledge graphs, and an integrated MCP server to analyse simulated data lineage and constraints.
NOASSERTION -
Bidirectional data lineage graph for Power BI (.pbix) files, from source to display
pypi -
Column-level lineage for dbt, SQL, Airflow and Dagster: formulas composed to sources, lineage checked against the data, business definitions, and pull request review. CLI, Python API, MCP server and GitHub Action.
MIT ★ 3 -
meok-mcp-data-governancegithub.com/meok-ai-labs/mcp-data-governanceupdated this year
MCP server for data governance, lineage, and quality scoring
npm MIT -
data-context-mcpupdated this year
Standalone MCP server for data context and catalog — search, lineage, docs, impact analysis
npm Apache-2.0 -
MCP server for Microsoft Data Platform projects: lets AI assistants analyse and safely edit semantic models, find where measures are used in PBIR reports, and trace lineage from the SQL source column to the report visual.
pypi MIT ★ 1 -
Bring your data platform to AI agents — an open MCP server exposing metadata, lineage, and metrics as first-class agent tools
MIT -
Data orchestration framework on ClickHouse: plain-Python pipelines, dynamic task graphs, containerized runs, lineage over MCP
pypi MIT -
Of everything downstream of a data change, what actually matters and who to tell. DataHub lineage over MCP, deterministic, written back into the graph.
Apache-2.0 -
agentic-datagithub.com/agentralabs/agentic-dataupdated this year
Universal data comprehension for AI agents — infer schemas, track lineage, detect anomalies, transform any format. 122 MCP tools, 16 parsers. Rust core + CLI + MCP server.
cargo MIT -
RAG-powered data catalog assistant: semantic search, data lineage, change-impact analysis, and NL->SQL - exposed via a Gradio UI, a FastAPI REST API, and a protocol-compliant MCP server.
MIT -
An open-source, AI-powered data engineering workspace for automated SQL/SAS lineage discovery, dependency visualization, column usage analysis, impact assessment, and developer productivity.
Apache-2.0 ★ 2 -
AgentsMeristemgithub.com/Vector897/AgentsMeristemupdated this year
Lineage-native root-cause for any AI agent. When data breaks, AgentsMeristem walks the DataHub lineage graph to the real upstream cause, probes the actual data, and writes the finding back as a DataHub incident — running local as a 7B any agent can call over MCP.
Apache-2.0 -
architecture-discovery-mcpgithub.com/rdtan/architecture-discovery-mcpupdated this year
Auto-discover enterprise architecture artifacts from Java/Maven source code. Scan your project and generate TOGAF-standard deliverables in seconds — application architecture, data architecture, and data lineage.
★ 6 -
MCP agent for semantic metrics governance with built-in trust scoring, lineage visualization, and conversational metric definition. Designed for data teams working with dbt, LookML, and modern semantic layers.
★ 5 -
twingithub.com/Jennycruzy/twinupdated this year
Chaos engineering for data platforms. Reads lineage and ownership from DataHub over MCP, predicts what a failure will break, then actually breaks it in a disposable shadow schema to find out whether the prediction was right.
Apache-2.0 -
Local-first repository analysis engine: code structure, dependency impact, and data lineage via CLI, Python API, and a read-only MCP server. Deterministic by default.
pypi Apache-2.0 ★ 1 -
Plataforma local-first de inteligência de código e arquitetura, com grafos de dependências, análise de impacto, Data Lineage e contexto para agentes de IA.
pypi Apache-2.0 -
Persistent architecture memory for AI coding agents via MCP. Design or reverse-engineer software architecture, explore ERDs and data lineage, and keep processor transformations aligned with code. Includes Claude Code and Codex plugins, skills, and samples.
MIT ★ 13 -
Ontology-driven codebase indexer and query service. Parses C#, TypeScript/JS, Go, Python, and SQL into an embedded graph database. Exposes Model Context Protocol (MCP) tools for AI agents to perform deep static analysis, cross-project call-graph tracing, and data lineage mapping.
nuget MIT ★ 18 -
Ask your data. Get answers your team has verified. Open-source analytics workbench where every answer is labelled Certified, From Metrics or Needs review. Works on your dbt project or straight on your database, with lineage, Apps and an MCP server for Claude, Codex and Cursor.
Apache-2.0 ★ 2 -
An MCP server that turns a question about your data into a multi-step GIS analysis, run by deterministic engines, with a lineage manifest beside every output.
npm AGPL-3.0 ★ 2 -
CodeRadargithub.com/officialCodeWork/CodeRadarupdated this year
React & TypeScript static analysis that maps every UI component to the APIs, state, and events behind it — and serves that context to AI coding agents over MCP. Screenshot or ticket in; component, data lineage, user journeys, and blast radius out. Deterministic, no LLM in the core.
MIT -
openmetadata-mcp-servergithub.com/us-all/openmetadata-mcp-serverupdated this year
OpenMetadata MCP server — 156 tools for metadata management, lineage, semantic search, data quality, and more. Read-only by default.
npm MIT -
Test data management: format-preserving masking, referential subsetting, privacy metrics, audit lineage, and a CI release gate. Python and FastAPI.
MIT ★ 1 -
Local-first retail data platform built with Kafka, PostgreSQL, dbt, Slim CI, metadata and lineage, read-only MCP, and Codex Skills for evidence-based incident diagnosis.
-
-semantic-metrics-modeling-assistantgithub.com/venugopal743/-semantic-metrics-modeling-assistantupdated this year
MCP agent for semantic metrics governance with built-in trust scoring, lineage visualization, and conversational metric definition. Designed for data teams working with dbt, LookML, and modern semantic layers.
★ 1 -
Open-source ETL/ELT you deploy on your own servers or cloud. Built on DuckDB: no-code/low-code visual pipelines or SQL, 426 components, dbt, CDC, data quality, reverse ETL, lineage, MCP for AI agents. No vendor cloud, no per-row billing.
pypi Apache-2.0 ★ 1,573 -
duckdb-dbt-mcpgithub.com/ajithshetty/duckdb-dbt-mcpupdated this year
A conversational MCP server that gives Claude direct access to your dbt project and DuckDB — query tables, run models, test data quality, and explore lineage, all in plain English.
-
Local-first AI/ML research curation: Quick Search, Learning Path, Research Lineage, Trending Feed, My Feed, Venues. Data from Semantic Scholar, HuggingFace, GitHub. MCP server included.
MIT ★ 2 -
mcp-databricks-servergithub.com/RafaelCartenet/mcp-databricks-serverupdated this year
Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understand relationships, discover notebooks/jobs, and execute queries - greatly reducing ad-hoc query time.
MIT ★ 43 -
lineage-relaygithub.com/Peanuts1605/lineage-relayupdated this year
MCP-backed release decisions for risky data schema changes.
Apache-2.0 -
PR-time dbt lineage, impact analysis and rebuild plans — no warehouse, no Python. CLI, TUI, GitHub Action and MCP server, written in Rust.
pypi MIT ★ 23 -
Tableau Workbook Auditor: free, in-browser auditing and lineage for Tableau workbooks (.twbx/.twb). Dead fields, duplicate calculations, performance lint, workbook diffs, dependency graphs, stored SQL. Nothing is uploaded.
npm MIT ★ 8 -
Enterprise MCP integration layer for PostgreSQL, Vertica, Airflow, logs, metadata and lineage with governed access controls.
MIT -
MCP agent that generates Apollo GraphQL servers from BigQuery queries with Dataplex lineage tracking
Apache-2.0 -
LineageIQ: read-only lineage, catalog and governance mapper for Microsoft Fabric, with a 2D/3D graph, REST API and MCP servers
MIT -
Graph-backed certification for high-risk data changes, powered by DataHub MCP.
Apache-2.0 ★ 1 -
leveegithub.com/TheWeirdDee/leveeupdated this year
Pre-commit dbt lineage guardian powered by DataHub's MCP Server — blocks breaking schema changes, generates the fix, writes back to the graph
Apache-2.0 -
Power BI & Microsoft Fabric Architecture Portal: 16:9 Report X-Ray, Visual-to-SQL & Dataflow Gen1/Gen2 Lineage, Star-Schema PDF, SharePoint Publish & MCP
MIT ★ 56 -
OvalEdge MCP Server
MIT -
secoda-analysis-mcpgithub.com/mbrummerstedt/secoda-analysis-mcpupdated this year
Read-only MCP server for exploring and analysing a Secoda data catalog
pypi Apache-2.0 -
adf-graphgithub.com/hurleysk/adf-graphupdated this year
MCP server that builds a queryable dependency graph from ADF pipeline artifacts
npm MIT -
datahub-chaperonegithub.com/praisejxy/datahub-chaperoneupdated this year
A governance proxy that makes AI agents accountable citizens of the DataHub context graph. Decides from catalog metadata what an agent may do - allow, redact, review, deny - and writes its findings back as aiAgent lineage.
Apache-2.0 -
coalesce-catalog-mcpgithub.com/jessemarshall/coalesce-catalog-mcpupdated this year
MCP server for the Coalesce Catalog Public GraphQL API; covers tables, columns, dashboards, lineage, governance, and asset metadata across the warehouse and BI layer.
npm MIT -
premortem-datahubgithub.com/prasadt1/premortem-datahubupdated this year
Premortem — how it breaks, before you merge (DataHub schema-change rehearsal)
Apache-2.0 -
Web UI for datagraph: pick a driver, database and schema, and get lineage, relationships, profiling, a dimensional model, PII and usage - with an MCP server for your AI assistant. Runs on a laptop or as a shared server with accounts.
pypi Apache-2.0 -
Auditable, local-first data & AI dataset workbench: multimodal evidence, traceable metric Q&A, and human-approved Agent/MCP actions.
Apache-2.0 ★ 156 -
Java-based MCP server for secure database query and management. Supports Oracle, MySQL, PostgreSQL with BYOK, CDC, lineage tracking, and SQL optimization.
Apache-2.0 ★ 1 -
Read-only MCP server for Tableau lineage and impact analysis over the Metadata API (GraphQL). Works on Tableau Server and Cloud.
pypi MIT ★ 2 -
Strata is a notebook your coding agent can drive, and everything it computes stays.
pypi Apache-2.0 ★ 5 -
Open, MCP-native training-data foundry: turn permitted documents into traceable, quality-gated SFT and preference datasets.
Apache-2.0 ★ 1 -
Explain changing SEO findings with versioned evidence, deterministic replay, transparent evaluation, and local MCP tools.
MIT -
Keeps knowledge in files, databases and Git while giving AI agents one verified way to read, propose and confirm changes.
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 -
LLM distillation detection & model fingerprinting via statistical forensics — behavioral probing, stylistic signatures & representation similarity. CLI + MCP ready.
MIT ★ 2 -
Data Workers MCP agents. Data Workers is the Autonomous Agentic Data Platform: reduce your data ops to zero, with agents that run the whole data platform. The platform lives at dataworkers.io.
npm NOASSERTION ★ 14 -
EKOS is an AI-native platform that continuously reconstructs, compiles, stores and serves enterprise knowledge.
cargo MIT ★ 28 -
Memory integrity for DataHub agents — agent memories that expire when the schema, glossary, or ownership beneath them changes. Built on DataHub's Timeline API, Documents and structured properties, with an MCP server for agents.
Apache-2.0