mcp-snowflake-server
MCP Snowflake Server NSP - A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants
Documentation
Snowflake MCP Server NSP
A Model Context Protocol (MCP) server / MCP server that connects AI assistants to Snowflake — enabling SQL queries, schema exploration, and data insights directly from your LLM client.
Highlights:
- Multiple authentication methods: password, key-pair, external browser, OAuth 2.0 (client credentials & bearer token), TOML connection files
- TOML multi-connection config — manage `production`, `staging`, and `development` environments in one file
- Write-safety guard — write operations are disabled by default and must be explicitly enabled
- Exclusion patterns — filter out databases, schemas, or tables from discovery
- `--exclude-json-results` flag — reduces LLM context window usage
- Selective tool exclusion via `--exclude_tools`
- Prefetch mode — pre-load table schema as MCP resources
- Docker support with hardened image (DHI, nonroot user, no shell in runtime)
Table of Contents
- Snowflake MCP Server NSP
Quick Start
The fastest way to try it — using `uvx` with a TOML connection file:
# 1. Create a connections file
cat > ~/snowflake_connections.toml **Contributing or running from source?** See [`CONTRIBUTING.md`](./CONTRIBUTING.md) for local development setup, test commands, formatting, and building the Docker image from source.
---
### Via UVX
TOML configuration (recommended)"mcpServers": {
"snowflake_production": {
"command": "uvx",
"args": [
"--python=3.13",
"--from", "mcp-snowflake-server-nsp",
"mcp_snowflake_server",
"--connections-file", "/path/to/snowflake_connections.toml",
"--connection-name", "production"
// Optional flags — see Configuration Reference
]
},
"snowflake_staging": {
"command": "uvx",
"args": [
"--python=3.13",
"--from", "mcp-snowflake-server-nsp",
"mcp_snowflake_server",
"--connections-file", "/path/to/snowflake_connections.toml",
"--connection-name", "staging"
]
}
}
Individual parameters"mcpServers": {
"snowflake": {
"command": "uvx",
"args": [
"--python=3.13",
"--from", "mcp-snowflake-server-nsp",
"mcp_snowflake_server",
"--account", "your_account",
"--warehouse", "your_warehouse",
"--user", "your_user",
"--password", "your_password",
"--role", "your_role",
"--database", "your_database",
"--schema", "your_schema"
// Optional: "--private_key_file", "/absolute/path/key.p8"
// Optional: "--private_key_file_pwd", "passphrase"
// Optional flags — see Configuration Reference
]
}
}
---
### Via Docker Hub
The image is published on [Docker Hub](https://hub.docker.com/r/nsphung/mcp-snowflake-server-nsp) — no build step required:docker pull nsphung/mcp-snowflake-server-nsp
> **Note:** `-i` (`--interactive`) is required to keep stdin open for the MCP stdio transport. Do **not** use `-d` (detach).
Claude Desktop — claude_desktop_config.json
With `.env` file (see [Authentication](#authentication)):"mcpServers": {
"snowflake": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"--env-file", "/absolute/path/to/.env",
"nsphung/mcp-snowflake-server-nsp"
]
}
}
With TOML connections file:"mcpServers": {
"snowflake": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/path/to/snowflake_connections.toml:/app/snowflake_connections.toml:ro",
"nsphung/mcp-snowflake-server-nsp",
"--connections-file", "/app/snowflake_connections.toml",
"--connection-name", "production"
]
}
}
VS Code — .vscode/mcp.json
With `.env` file:"snowflake": {
"type": "stdio",
"command": "docker",
"args": [
"run", "--rm", "-i",
"nsphung/mcp-snowflake-server-nsp"
],
"envFile": "${workspaceFolder}/.env"
}
With TOML connections file:"snowflake": {
"type": "stdio",
"command": "docker",
"args": [
"run", "--rm", "-i",
"-v", "/path/to/snowflake_connections.toml:/app/snowflake_connections.toml:ro",
"nsphung/mcp-snowflake-server-nsp",
"--connections-file", "/app/snowflake_connections.toml",
"--connection-name", "production"
]
}
OpenCode — opencode.jsonc"snowflake": {
"type": "local",
"command": [
"docker", "run", "--rm", "-i",
"--env-file", "/absolute/path/to/.env",
"nsphung/mcp-snowflake-server-nsp"
],
"enabled": true,
"timeout": 300000
}
---
## Configuration Reference
All connection parameters can also be set as environment variables (`SNOWFLAKE_`).
| Flag | Env var | Default | Description |
| ------------------------------ | -------------------------------- | ------------ | -------------------------------------------------------------------------------------------------- |
| `--account` | `SNOWFLAKE_ACCOUNT` | — | Snowflake account identifier |
| `--user` | `SNOWFLAKE_USER` | — | Snowflake username |
| `--password` | `SNOWFLAKE_PASSWORD` | — | Password (not required for key-pair / SSO) |
| `--warehouse` | `SNOWFLAKE_WAREHOUSE` | — | Virtual warehouse to use |
| `--database` | `SNOWFLAKE_DATABASE` | _(required)_ | Default database |
| `--schema` | `SNOWFLAKE_SCHEMA` | _(required)_ | Default schema |
| `--role` | `SNOWFLAKE_ROLE` | — | Role to assume |
| `--private_key_file` | `SNOWFLAKE_PRIVATE_KEY_FILE` | — | Absolute path to RSA or ECDSA (ES256/384/512) private key file (`.p8` / `.pem`) |
| `--private_key_file_pwd` | `SNOWFLAKE_PRIVATE_KEY_FILE_PWD` | — | Passphrase for encrypted private key |
| `--connections-file` | — | — | Path to TOML connections file |
| `--connection-name` | — | — | Connection profile name in TOML file (required with `--connections-file`) |
| `--allow_write` | — | `false` | Enable `write_query` and `create_table` tools |
| `--prefetch` / `--no-prefetch` | — | `false` | Pre-load table schema as `context://table/*` resources (disables `list_tables` / `describe_table`) |
| `--exclude_tools` | — | `[]` | Space-separated list of tool names to disable |
| `--exclude-json-results` | — | `false` | Omit embedded JSON resources from responses (reduces context window usage) |
| `--log_dir` | — | — | Directory for log file output |
| `--log_level` | — | `INFO` | Log verbosity: `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` |
---
## Exclusion Patterns
Edit [`runtime_config.json`](https://github.com/nsphung/mcp-snowflake-server/blob/main/runtime_config.json) to exclude databases, schemas, or tables from all discovery tools. Patterns are matched case-insensitively as substrings.{
"exclude_patterns": {
"databases": ["temp"],
"schemas": ["temp", "information_schema"],
"tables": ["temp"]
}
}
The server loads this file automatically at startup from the working directory.
---
## License
This project is licensed under the **MIT License**. See the [`LICENSE`](https://github.com/nsphung/mcp-snowflake-server/blob/main/LICENSE) file for the full text.
---
## Fork and Attribution
This repository is a fork of [`isaacwasserman/mcp-snowflake-server`](https://github.com/isaacwasserman/mcp-snowflake-server).
[](https://mseep.ai/app/isaacwasserman-mcp-snowflake-server)
- Upstream authors and contributors retain copyright for their contributions.
- Fork-specific changes are maintained by `nsphung`.
- A summary of notable modifications is tracked in [`NOTICE`](https://github.com/nsphung/mcp-snowflake-server/blob/main/NOTICE).Frequently asked questions
What is mcp-snowflake-server?
mcp-snowflake-server is MCP Snowflake Server NSP - A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants
How do I install mcp-snowflake-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-snowflake-server open source?
Yes — it is hosted on GitHub at https://github.com/nsphung/mcp-snowflake-server and has 2 stars.
Related MCP tools
sembleFast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
mcp-context-forgeAn AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
fastmcp🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
mcpAWS MCP Servers — helping you get the most out of AWS, wherever you use MCP. Python-based implementation. Trusted by 6900+ developers.
tradingview-mcpTradingView MCP server — real-time market data, technical analysis, screeners & backtesting for Claude, ChatGPT, Cursor & any MCP client. Stocks, crypto, forex & futures across global exchanges. Hosted or self-host.
jcodemunch-mcpCut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP