📅 Book a 30-min Demo📞 Call/text (571) 293-0242
Connector · Cloud data warehouse

Snowflake MCP Server & Agent Skill

Last updated

ibl.ai publishes a free Snowflake agent skill: a SKILL.md that teaches an AI agent to read and write Snowflake data and expose it as an MCP tool. Download it, connect your own Snowflake credentials, and run the agent on ibl.ai Agentic OS, where you own all the code and the data.

Snowflake holds an organization's analytical data in databases, schemas, tables and views, plus semantic models, search services and Cortex AI objects governed by roles.

What is the Snowflake API, and what can an agent read from it?

The SQL API submits SQL (queries, DDL, DML, multiple statements, stored procedure calls), checks status and cancels statements. Cortex Analyst and Cortex Search are exposed through the managed MCP server.

  • API: Snowflake SQL API; Snowflake-managed MCP server (Cortex) (REST)
  • Access: Issued by your administrator
  • Base URL: https://{account_identifier}.snowflakecomputing.com/api/v2/statements
  • Authentication: OAuth (Snowflake OAuth or External OAuth); Key-pair JWT; Programmatic access token; Workload identity federation

An account administrator creates a user or service user, assigns a role and sets up OAuth, a key pair or a programmatic access token. Queries run with that role's privileges.

Send Authorization: Bearer with the token; optional X-Snowflake-Authorization-Token-Type (OAUTH, KEYPAIR_JWT). Key-pair JWTs are signed with the user's private key and include the public key fingerprint.

What can an agent read from Snowflake?

  • SQL query results — POST /api/v2/statements with a SELECT; bind variables via the bindings field.
  • Statement status — GET /api/v2/statements/{statementHandle} polls a long-running statement and returns results.
  • Natural-language analytics — Cortex Analyst generates SQL from a question (managed MCP server tool).
  • Unstructured search — Cortex Search services search documents and text (managed MCP server tool).

What can an agent write to Snowflake?

  • DML — INSERT, UPDATE, DELETE and MERGE through the SQL API. Confirm with the user first.
  • DDL and provisioning — Create tables, users and roles through the SQL API, subject to role privileges. Confirm with the user first.
  • Cancel statement — Cancel a running statement by its handle.

Limits: Statements may run asynchronously; poll by statementHandle. Timeout defaults to STATEMENT_TIMEOUT_IN_SECONDS. HTTP 429 means too many requests; retry with requestId and retry=true to avoid running a statement twice.

Warehouses often hold customer records, financial data and other regulated data (PII, PHI, cardholder data) depending on what the organization loads; access follows role grants.

How do I connect Snowflake to an AI agent over MCP?

Snowflake publishes an official MCP server: Snowflake-managed MCP server.

GA. A schema object at /api/v2/databases/{db}/schemas/{schema}/mcp-servers/{name} exposing Cortex Agents, Analyst, Search, SQL (optional read-only) and custom tools. Up to 50 tools.

You can register that server on ibl.ai as it is, or use the SKILL.md below when you want the agent to call the Snowflake SQL API; Snowflake-managed MCP server (Cortex) directly.

On ibl.ai an MCP connection is three records, and a working integration always needs all three:

  1. Register the server — POST …/mcp-servers/ with its URL, a transport (sse, websocket or streamable_http) and an auth_type of none, token or oauth2.
  2. Create a connection that holds the credential, scoped to the whole organization (platform), to a single agent, or to each user (user).
  3. Enable it on the agent — mcp-tool in tool_slugs and the server id in mcp_servers. Both lists are replaced, not merged, so read the settings first.

For an API key or a service credential, one token connection at platform scope serves the whole organization; scope a connection to a single agent when that agent needs narrower access than the rest.

The field reference is in MCP server connections, and the /iblai-api-agent-mcp skill runs all three steps from a coding agent.

What does the Snowflake agent skill do?

The Snowflake skill is one SKILL.md file named iblai-connect-snowflake. It gives an agent the auth conventions, what to read, which writes need a person's confirmation, the ibl.ai MCP wiring, example prompts and guardrails.

Download the Snowflake SKILL.md

Save it as .claude/skills/iblai-connect-snowflake/SKILL.md, or in your agent's skills folder. The ibl.ai platform skills it calls come from one install:

$ npx skills add iblai/vibe --all

This connector skill is a starting point maintained on ibl.ai, not part of the iblai/vibe repository.

It was checked against Snowflake's documentation on October 20, 2026. Test it against your own Snowflake setup before you rely on it.

What can I ask a Snowflake agent to do?

  • “What was net revenue by region last quarter, and how did it compare to the prior quarter?”
  • “Show the top 20 customers by lifetime value from the ANALYTICS.SALES schema”
  • “Search our support transcripts for complaints about the new billing page”
  • “Which tables in the FINANCE database were modified in the last 7 days?”

How do I run a Snowflake agent on ibl.ai?

Agentic OS is where the agent runs on ibl.ai: it holds the Snowflake MCP connection, the model the agent uses, its instructions and its conversation history.

On ibl.ai you own all the code and the data, run it model-agnostic across any LLM, and pay with no per-seat pricing — so you can deploy anywhere, from your own cloud to a fully air-gapped network.

Which ibl.ai agents work with Snowflake data?

Which ibl.ai platform skills does a Snowflake agent use?

What else should I know before connecting Snowflake to an AI agent?

Is there an official Snowflake MCP server?

Yes. Snowflake publishes Snowflake-managed MCP server.

You can register it on ibl.ai as an MCP server, or use the SKILL.md when you want the agent to call the Snowflake SQL API; Snowflake-managed MCP server (Cortex) directly.

Who can get Snowflake API credentials?

An account administrator creates a user or service user, assigns a role and sets up OAuth, a key pair or a programmatic access token. Queries run with that role's privileges.

Does Snowflake data leave my infrastructure when an ibl.ai agent uses it?

On ibl.ai, you own all the code and the data. Self-hosted in your cloud or data center, the agent, its MCP connections and its conversation logs stay inside your perimeter.

Because the platform is model-agnostic, you can point the agent at a model you host, so Snowflake records need not reach a third-party model provider.

Is the Snowflake agent skill free to use?

Yes. The SKILL.md is a free download with no sign-up. It assumes you already have Snowflake credentials, and your agreement with Snowflake still governs how you use its API.

Which other data sources can an AI agent connect to alongside Snowflake?

Which other Enterprise systems have a connector?

Every connector, grouped by sector, is on the connectors hub.