MCP Snowflake Server NSP

Created By
nsphung2 days ago
A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants
Overview

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, 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

Server Config

{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "--python=3.13",
        "--from",
        "mcp-snowflake-server-nsp",
        "mcp_snowflake_server",
        "--connections-file",
        "/absolute/path/to/snowflake_connections.toml",
        "--connection-name",
        "myconn"
      ]
    }
  }
}
Project Info
Created At
2 days ago
Updated At
2 days ago
Author Name
nsphung
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Scratchpad Mcp
@MikePressure

scratchpad-mcp is an MCP server that gives AI agents persistent, token-efficient storage. It solves a specific waste problem: agents constantly re-read files they've already seen, re-summarize documents they've already processed, and re-load context they've already understood. Every one of those round-trips burns tokens for no new information. This server fixes that with eight tools designed around how agents actually work: Versioned writes. write_file automatically versions every write and keeps the 10 most recent versions per file. Storage is append-only on success and atomic on failure partial writes can't corrupt state. Structured diffs. read_file accepts a since_version parameter and returns a JSON line-diff against that prior version instead of the full content. Agents that have already seen v1 can ask "what changed in v3?" and get a small structured payload they can reason about, not the entire file again. Append-only logs. append_log and read_log give agents an event-stream they can replay. Cursor-based pagination (since_entry + last_entry_id + has_more) means an agent can checkpoint where it left off and resume cheaply. On-demand summaries. summarize_file calls Claude Haiku to summarize files over ~2000 estimated tokens. Summaries are cached per file version, so repeat calls on an unchanged file cost nothing. The threshold is enforced server-side you can't accidentally pay to summarize something small. Per-agent isolation. Every operation is scoped by an agent_id parameter, so one server instance can serve many agents without leaking state between them. Storage limits. 1 MB per file write, 64 KB per log entry, 1000 files / 100k log entries / 100 MB total per agent sane multi-tenant guardrails out of the box. Backed by a single SQLite file (Postgres migration is on the roadmap). All SQL is parameterized, paths are validated against a strict allowlist, and the security model is documented honestly it's safe for one-user-per-process deployments today, and the V2 plan derives agent_id from the caller's API key for true multi-tenancy. Build agents that remember what they've already seen.

a day ago
Wiza

9 hours ago