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.
-
adk-snowflake-agentgithub.com/YuriyYakovlev/adk-snowflake-agentupdated this year
Snowflake AI Agent (ADK, Snowflake MCP)
-
snowflake-atlasgithub.com/sagar-shirwalkar/snowflake-atlasupdated this year
Local-first AI knowledge layer for Snowflake documentation via MCP
Apache-2.0 -
—
MIT -
snowflake-mcpgithub.com/igbokwe-emeka/snowflake-mcpupdated this year
—
-
snowflake-mcpgithub.com/lpanigrahi/snowflake-mcpupdated this year
—
Apache-2.0 -
—
-
—
-
MCP Server for Snowflake — exposes Snowflake operations as MCP tools
npm MIT -
snowflake-mcp-demogithub.com/gustav-lindstrom/snowflake-mcp-demoupdated this year
—
-
—
GPL-3.0 ★ 184 -
—
GPL-3.0 -
MCP Server for connecting to Snowflake with read-only questions
MIT ★ 14 -
MCP server implementation for Snowflake integration
MIT ★ 5 -
—
-
—
MIT -
—
Apache-2.0 -
—
GPL-3.0 -
Docker image for MintMCP hosted Snowflake MCP
Apache-2.0 -
—
MIT -
General-Purpose Snowflake MCP server for any type of SQL operation
MIT ★ 3 -
Snowflake-MCPgithub.com/Jeremy-Demlow/Snowflake-MCPupdated this year
Repo To Showcase MCP
-
Model Context Protocol server for Snowflake database integration
npm MIT -
Simple and clean Snowflake MCP with read-only permissions so that users can ask Natural Language questions against their Snowflake databases
npm ★ 5 -
Building out mcp server for snowflake mainly intended to access and use snowflake account_usage data
★ 1 -
MCP server for Stellar Design System
npm SEE LICENSE IN LICENSE -
Enterprise Model Context Protocol (MCP) server for Snowflake data cloud and Cortex AI.
Apache-2.0 ★ 1 -
Un servidor MCP para interactuar con Snowflake usando el protocolo Model Context Protocol
-
Self-hosted MCP server for secure AI access to Snowflake data warehouses.
NOASSERTION -
czechitas-snowflake-mcpgithub.com/IShalkin/czechitas-snowflake-mcpupdated this year
Model Context Protocol (MCP) server connecting an AI agent to Snowflake for natural-language querying over a database.
-
A simple Streamlit application that demonstrates Snowflake MCP (Model Context Protocol) capabilities for natural language querying.
MIT ★ 1 -
snowflake_mcpgithub.com/sunil-dhaka/snowflake_mcpupdated this year
Read-only MCP server for Snowflake — query, explore schemas, and save results with built-in safety constraints
-
MCP Snowflake Server NSP - A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants
pypi MIT ★ 2 -
A local Python-based MCP server that connects Claude to Snowflake, enabling natural language SQL execution, schema exploration, and database operations through a secure, customizable tool interface
-
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
-
PostgreSQL port of a Snowflake AI analytics lab: dbt, row-level security, and a DeepSeek agent + MCP server with pgvector/full-text search.
Apache-2.0 -
Clean-room, Rust-first, Asupersync-native Snowflake SQL API connector for coding agents: deterministic JSON envelopes, capability registry, MCP server, TUI. 14 crates on crates.io; live reads proven at the driver level, writes implemented but end-to-end live run still pending. No ODBC, JDBC, or Tokio.
cargo NOASSERTION ★ 7 -
Multi-source AP invoice pipeline on Snowflake: Dynamic Tables, a Cortex Agent on a semantic view with tested stored-procedure tools and answer-amount checks, MCP for Claude, a BR-004 data-quality guardrail and a CI-gated native agent evaluation, with preserved live evidence
-
Metatate plugin for Snowflake Cortex Code using Snowflake-managed MCP
MIT -
streamlit_mcp_cortexgithub.com/shashankthimmegowda/streamlit_mcp_cortexupdated this year
Streamlit app powered by Snowflake Cortex AI and MCP (Model Context Protocol) for natural language querying and AI-driven analytics directly in Snowflake. Stack: Python · Streamlit · Snowflake Cortex · MCP
MIT -
MCP server for Fresha Data Connector via Snowflake
npm MIT -
@rohithgmurali/snowflakemcpupdated this year
Model Context Protocol server for Snowflake — run via npx
npm MIT -
AI data engineering platform: Snowflake + dbt + Dagster + a custom MCP server for natural-language warehouse queries
MIT -
Extract every UUID, ULID, NanoID, ObjectId and Snowflake, and decode the time inside
npm MIT ★ 1 -
Define a metric once, serve it everywhere: a spec, a linter, an MCP server for AI agents, a query gate, a CLI, and a Snowflake semantic view compiler.
MIT -
MCP server for generating IDs with different algorithms including Snowflake compatible with MyBatis-Plus
npm MIT -
Runnable twins of Postgres, REST, and Snowflake contracts, with an MCP server so agents and tests never touch production.
npm MIT -
Natural-language analytics over a governed Snowflake warehouse: LangGraph agent, MCP tool server, role-based PII masking, eval harness, Terraform on AWS.
-
database-mcpgithub.com/nitaiaharoni1/database-mcpupdated this year
Model Context Protocol server for multi-database access (PostgreSQL, MySQL, SQLite, Snowflake) with comprehensive introspection and analysis tools
npm MIT -
Pre-flight query cost and result-size guardrails for AI agents across BigQuery, Snowflake, and Databricks
go MIT ★ 1 -
Remote MCP server giving LLM agents typed, audited, read-only access to PostgreSQL, Snowflake and REST APIs (JWT, RBAC, SQL-AST guard, rate limits).
MIT -
cortex-code-neo4j-mcpgithub.com/neo4j-field/cortex-code-neo4j-mcpupdated this year
Snowflake Cortex Code MCP server that connects Cortex agents to Neo4j Aura via the Aura REST API for graph-backed enterprise AI workflows.
Apache-2.0 -
dagsmithgithub.com/tmcwilliam707/dagsmithupdated this year
Agentic scaffolding for data engineering — turns natural-language source specs into tested Snowflake pipelines (dbt + Airflow + GE) via an LLM tool-use loop over an MCP metadata server.
MIT ★ 1 -
Snowflake-hosted MCP server providing semantic search over Snowflake troubleshooting rules and best practices
Apache-2.0 -
A production-ready Salesforce integration platform unifying Gemini 3.6 Flash AI, Slack Socket Mode, Gmail, Google Calendar, and Snowflake through Model Context Protocol (MCP).
-
Agent IA gouverné : questions métier en français sur dbt + Snowflake via MCP, sans SQL libre, bloqué par la qualité des données (Soda) et évalué en CI.
MIT -
End-to-end data pipeline: S3 → Snowflake → dbt → Airflow, gated by GitHub Actions CI/CD. Extended with an AI agent layer: MCP server, Cortex vector search, agent-diagnosed bug fix shipped through CI.
MIT -
Turbofan failure prediction (NASA C-MAPSS) on a governed semantic layer: Snowflake feature store, tandem XGBoost, Cortex Analyst and MCP, ported to Databricks with Unity Catalog metric views and a live Genie app.
MIT ★ 1 -
Vendor-neutral semantic model that makes a warehouse legible to LLMs: validator, compilers to Snowflake semantic views, Apache Ossie, and dbt MetricFlow, an MCP server over governed metrics, and an eval that measures the accuracy gain.
MIT -
MCP server that gives AI agents fast, read-only access to SQL Server and Snowflake schema metadata — tables, columns, foreign keys, and smart join path suggestions — via a local cache. No live queries needed for exploration.
GPL-3.0 -
A production-style data platform that ingests from three heterogeneous sources (PostgreSQL, MongoDB, REST API), loads into Snowflake, transforms through dbt staging and intermediate layers with automated quality checks, orchestrates with Prefect, deploys via dbt Cloud CI/CD, and exposes models to AI agents through a dbt MCP server.