snowflake-mcp

snowflake-mcp is a skill for Claude Code, Codex from christianclaudio/mcp-server-snowflake. It costs 45 tokens per session (1,454 once invoked), scanned A, original, Apache-2.0.

A set of instructions for AI agents working with Snowflake, a cloud service for storing and analysing data. It covers databases, warehouses, data pipelines, governance, and Cortex AI through an MCP server.

In plain words
What is it for?
Table migrations, zero-copy clones, query scaling, streaming pipelines, schema management, governance, and Cortex AI tasks.
Why use it?
It gives agents structured procedures and safety checks for inspecting data, changing schemas, scaling queries, and managing Snowflake workloads.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Table migrations, zero-copy clones, query scaling, streaming pipelines, schema management, governance, and Cortex AI tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/christianclaudio/mcp-server-snowflake/snowflake-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add christianclaudio/mcp-server-snowflake --skill snowflake-mcp
Clone the repo
git clone --depth 1 https://github.com/christianclaudio/mcp-server-snowflake

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for snowflake-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp/github.svg)](https://agentmods.dev/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp)
Your own site
<a href="https://agentmods.dev/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp"><img src="https://agentmods.dev/badge/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for snowflake-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp"><img src="https://agentmods.dev/badge/skills/christianclaudio/mcp-server-snowflake/snowflake-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01454
Opus 5 $0.00023 $0.00727
Sonnet 5 $0.00009 $0.00291
Haiku 4.5 $0.00005 $0.00145

Measured 4d ago against content hash 8627f5f16d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

snowflake-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/snowflake-mcp/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Snowflake Data Cloud MCP Server (mcp-server-snowflake) Agent Skill

This skill provides expert operating guidelines, architectural recipes, and safety gates for AI agents orchestrating data workloads, schema management, virtual warehouses, streaming pipelines, and Cortex AI via mcp-server-snowflake.


🎯 Core Agent Recipes & Playbooks

1. Zero-Downtime Table Migration & Clones

  • Step 1: Inspect Current Structure — Call snowflake_inspect_table_with_sample(table_name=..., sample_rows=5) to verify columns, types, and data distribution.
  • Step 2: Instant Zero-Copy Backup — Invoke snowflake_clone_table_recipe(source_table=..., target_table="..._BACKUP_YYYYMMDD"). Zero-copy clones create metadata pointers instantly without storage overhead.
  • Step 3: Apply Schema / DML Changes — Use snowflake_execute_dml(statement=...) to alter table structures or populate new columns.
  • Step 4: Verify Data Profile — Run snowflake_profile_table(table_name=...) to validate row counts and column completeness.

2. High-Performance Query Scaling

  • Cost-Optimized Heavy Queries — Invoke snowflake_warehouse_scale_and_execute(warehouse_name="COMPUTE_WH", target_size="LARGE", query="...", restore_previous_size=True). This scales compute up for the heavy workload and restores the previous size afterwards. It does not suspend the warehouse. To stop credit consumption, call snowflake_suspend_warehouse when the work is complete.
  • Query Optimization — Before running unknown queries, call snowflake_get_query_plan(query=...) to inspect scan predicates and join pruning. After execution, analyze snowflake_get_query_operator_stats(query_id=...).

3. Continuous Data Pipelines (CDC & Tasks)

  • Change Data Capture — Create a stream via snowflake_create_stream(stream_name=..., on_table=...). Read incremental delta changes with snowflake_read_stream_changes(stream_name=...).
  • Scheduled Transformations — Deploy serverless or warehouse-backed tasks with snowflake_create_task(task_name=..., sql_statement=..., schedule="15 MINUTE"). Resume the task with snowflake_resume_task(task_name=...).

Read the full file on GitHub · 71 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago Changed · +6 lines 8627f5f16d75
  2. 10d ago First seen · 65 lines · 45 tokens per session scan A 379a16972725

Subscribe to this mod's changes

snowflake-mcp is a skill published in the GitHub repository christianclaudio/mcp-server-snowflake (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 45 tokens to every session and 1,454 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.