# Snowflake

> Inspect schemas and run SQL against a Snowflake account from an AI agent.

[Canonical HTML page](https://top-mcps.com/mcp/snowflake) · [server.json](https://top-mcps.com/mcp/snowflake.json) · [methodology](https://top-mcps.com/about/methodology)

## Install

### Claude Desktop — `claude_desktop_config.json`

Paste under mcpServers. Fully quit and reopen Claude after editing.

```json
{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-server"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### Claude Code — `CLI or .mcp.json`

Run from your repo. Commit .mcp.json to share with your team.

```shell
# export SNOWFLAKE_ACCOUNT=xy12345.us-east-1
# export SNOWFLAKE_USER=reader
# export SNOWFLAKE_PASSWORD=changeme
# export SNOWFLAKE_ROLE=READER_ROLE
# export SNOWFLAKE_WAREHOUSE=XS_AGENT_WH
# export SNOWFLAKE_DATABASE=ANALYTICS
claude mcp add snowflake -- uvx mcp-snowflake-server
```

### Cursor — `.cursor/mcp.json`

Global path: ~/.cursor/mcp.json. Reload window after editing.

```json
{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-server"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### VS Code — `.vscode/mcp.json`

VS Code uses the "servers" key (not "mcpServers").

```jsonc
{
  "servers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-server"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### Windsurf — `~/.codeium/windsurf/mcp_config.json`

Open via Cascade → hammer icon → Configure.

```json
{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-server"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### Cline — `cline_mcp_settings.json`

Open via the Cline sidebar → MCP Servers → Edit.

```json
{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-server"
      ],
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### Continue — `~/.continue/config.json`

Continue uses modelContextProtocolServers with a transport block.

```json
{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": [
            "mcp-snowflake-server"
          ],
          "env": {
            "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
            "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
            "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
            "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
            "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
            "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
          }
        }
      }
    ]
  }
}
```

### Codex CLI — `~/.codex/config.toml`

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

```shell
# ~/.codex/config.toml
[mcp_servers.snowflake]
command = "uvx"
args = [
  "mcp-snowflake-server",
]
env = { SNOWFLAKE_ACCOUNT = "${SNOWFLAKE_ACCOUNT}", SNOWFLAKE_USER = "${SNOWFLAKE_USER}", SNOWFLAKE_PASSWORD = "${SNOWFLAKE_PASSWORD}", SNOWFLAKE_ROLE = "${SNOWFLAKE_ROLE}", SNOWFLAKE_WAREHOUSE = "${SNOWFLAKE_WAREHOUSE}", SNOWFLAKE_DATABASE = "${SNOWFLAKE_DATABASE}" }
```

### Zed — `~/.config/zed/settings.json`

Zed calls them "context_servers". Settings live-reload on save.

```jsonc
{
  "context_servers": {
    "snowflake": {
      "command": {
        "path": "uvx",
        "args": [
          "mcp-snowflake-server"
        ]
      },
      "env": {
        "SNOWFLAKE_ACCOUNT": "${SNOWFLAKE_ACCOUNT}",
        "SNOWFLAKE_USER": "${SNOWFLAKE_USER}",
        "SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}",
        "SNOWFLAKE_ROLE": "${SNOWFLAKE_ROLE}",
        "SNOWFLAKE_WAREHOUSE": "${SNOWFLAKE_WAREHOUSE}",
        "SNOWFLAKE_DATABASE": "${SNOWFLAKE_DATABASE}"
      }
    }
  }
}
```

### ChatGPT — `ChatGPT → Apps directory`

Snowflake doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

```none

```

## At a glance

- **Maintainer:** Community
- **Transport:** stdio
- **Auth model:** API key
- **Required secrets:** SNOWFLAKE_ACCOUNT, SNOWFLAKE_USER, SNOWFLAKE_PASSWORD, SNOWFLAKE_ROLE, SNOWFLAKE_WAREHOUSE, SNOWFLAKE_DATABASE
- **Supported clients:** Claude, Cursor, VS Code, Windsurf, Any MCP-compatible client, Snowflake account
- **License:** MIT
- **Language:** Python
- **Latest version:** latest
- **Last verified:** 2026-06-02
- **GitHub stars:** 183 (fetched 2026-06-02T13:16:41.064Z)
- **Score:** 57/100 (rubric 2026-04 — see https://top-mcps.com/about/methodology)
- **Source:** https://github.com/isaacwasserman/mcp-snowflake-server

## Tools & permissions

| Tool | Description | Args | Side effects |
|------|-------------|------|--------------|
| `list_databases` | List databases visible to the connected role. | `—` | read |
| `list_schemas` | List schemas in a database. | `database: string` | read |
| `list_tables` | List tables in a schema. | `schema: string` | read |
| `describe_table` | Return columns, types, and clustering info for a table. | `table: string` | read |
| `query` | Run a SELECT statement and return rows. | `sql: string` | read |

## Security & scope

- **Access scope:** read-only
- **Sandbox:** Connects to a Snowflake account using key-pair or password auth. Read-only at the MCP tool layer; pair with a SELECT-only role and a resource-monitored XS warehouse to bound spend.
- **Gotchas:**
  - Snowflake is billed per warehouse-second. Always attach a resource monitor to the warehouse the MCP uses.
  - Static passwords in env are leak-prone — prefer key-pair auth and a key path the OS keychain can protect.
  - A privileged role connected here can drop tables. Scope to a SELECT-only role even on staging accounts.

## Quick answer

**What it does.** Connects to a Snowflake account and exposes database/schema/table enumeration, column metadata, and SELECT execution to AI models.

**Best for:**
- Schema discovery
- Analytical query drafting
- Cross-database joins inside one account
- Information schema audits
- Staging-account debugging

**Not for:**
- Write-heavy DML from an LLM
- Cost-sensitive workloads without a per-user resource monitor
- Multi-account federated queries

## Description

A community-maintained MCP that connects an AI agent to a Snowflake account. Lists databases, schemas, and tables, returns column-level metadata, and executes SELECT against a warehouse you choose at connect time. Authentication uses Snowflake key-pair auth or username/password; the safe default is a read-only role on a dedicated WAREHOUSE so an LLM cannot burn through credits accidentally.

## Why it matters

Snowflake is the dominant warehouse in mid-market and enterprise stacks. Getting an AI agent to draft and run analytical SQL against it without leaving Claude or Cursor closes the loop between question and answer.

## Key features

- Key-pair auth supported (no static passwords)
- Per-WAREHOUSE scoping at connect time
- Database / schema / table introspection
- INFORMATION_SCHEMA access
- Read-only-by-default tool surface

## FAQ

### Key-pair auth or password?

Key-pair is supported and recommended for production accounts — set SNOWFLAKE_PRIVATE_KEY_PATH instead of SNOWFLAKE_PASSWORD. Most teams keep password auth only for the staging-account MCP used by an agent.

### Does it pick the WAREHOUSE per query?

No — the WAREHOUSE is fixed at connect time. Create a dedicated XS warehouse (e.g. XS_AGENT_WH) with a resource monitor so the agent cannot accidentally scale up a production warehouse.

### Can the agent write?

Default tool set is SELECT-only. The role you connect with should also be SELECT-only as defence in depth; the MCP cannot enforce what the SQL actually does.

### Does it support OAuth or external browser auth?

External browser auth is not exposed because MCP servers are non-interactive. Use key-pair auth for service-style identities.

## Changelog

- **2026-06-02** — Refreshed install snippets and fact sheet; verified for 2026.
- **2025-01-22** — Initial directory listing.