MCP server
Snowflake MCP server
Snowflake's managed MCP server exposes admin-defined tools, such as Cortex agents, Cortex Analyst, Cortex Search and SQL, to AI assistants.
- Official server
- Databases
At a glance
- Maintained by
- Snowflake
- Tools exposed
- 5 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Snowflake is a data warehouse used by many mid-size and large companies for reporting and analytics. Its managed MCP server runs inside Snowflake, and an administrator decides which tools it exposes: Cortex agents, Cortex Analyst for questions in plain English, Cortex Search over documents, SQL execution and generic tools.
That design suits governed data. Instead of giving an assistant raw access, the data team publishes a small set of approved tools with Snowflake's own permissions behind them.
SQL execution is read-only by default, and write access must be granted explicitly in the server definition. Sign-in uses Snowflake OAuth or an external identity provider. The earlier open-source Snowflake Labs server is deprecated and points users to this managed server. Tool names depend on how your administrator sets it up.
Use cases
Best business use cases
Self-service analytics
Document search
Data agents
Governed access
Report drafts
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Admin-defined tools; SQL execution is read-only by default and write access must be granted in the server spec.
-
CORTEX_AGENT_RUNTool type: runs a Cortex Agent.
-
CORTEX_ANALYST_MESSAGETool type: asks Cortex Analyst about structured data through a semantic model.
-
CORTEX_SEARCH_SERVICE_QUERYTool type: queries a Cortex Search service over unstructured data.
-
SYSTEM_EXECUTE_SQLTool type: runs SQL; read_only defaults to true.
-
GENERICTool type: exposes a custom UDF or stored procedure.
Workflows
Example workflows
Ask the warehouse a question
-
1
The data team publishes a Cortex Analyst tool.
-
2
A manager asks for revenue by region last quarter.
-
3
The assistant calls the tool.
-
4
Snowflake runs governed SQL and returns results.
-
5
The assistant explains the numbers.
Search policy documents
-
1
Documents are indexed with Cortex Search.
-
2
A staff member asks a policy question.
-
3
The assistant calls the search tool.
-
4
It answers with the relevant passages.
-
5
Sources are shown for checking.
Prompts
Example prompts
“What was revenue by region last quarter, compared with the quarter before?”
“Find the policy section about travel expenses for contractors.”
“Which product lines grew fastest this year?”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Code: terminal
claude mcp add --transport http snowflake https://<account_url>/api/v2/databases/<database>/schemas/<schema>/mcp-servers/<name>- Hosted server: https://<account_url>/api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name} (created per account with CREATE MCP SERVER).
- Needs: Snowflake OAuth (default) or External OAuth (Okta, Entra ID); programmatic access token as an alternative; Account URL, database, schema and MCP server name.
- Claude Desktop: Add as a custom connector in Claude using the MCP server URL plus the OAuth client ID and secret from a Snowflake OAuth security integration. Docs give no mcpServers JSON block.
Security
Security considerations
-
Admin-defined tools
Only tools the administrator publishes are available.
-
Read-only SQL
SQL is read-only unless write access is granted.
-
Company sign-in
Use Snowflake OAuth or your identity provider.
-
Audit
Use Snowflake query history to review activity.
Related servers
Servers that pair well with it
BigQuery
Google's remote BigQuery MCP server lets AI list datasets and tables and run SQL, with a read-only query tool and IAM controls.
PostgreSQL
Lets AI assistants explore a PostgreSQL database, run SQL in a restricted read-only mode and check query performance and database health.
Elasticsearch
Elastic's Agent Builder MCP endpoint lets AI search indices, run ES|QL queries and read mappings and documents in Elasticsearch.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- Database design Data models that stay fast and correct as your business grows, with backups and access rules in place.
- Multi-tenant architecture One product serving many customer accounts, with each account's data kept separate and secure.
- Product scaling Keep a growing product fast and stable as users, data and features increase.
- Web applications Custom browser-based software for the work your team does every day, from booking tools to operations systems.
- Dashboards and reporting Dashboards that pull numbers from the systems you already use and show what matters without a spreadsheet.
Solutions
View all solutions- Automated reporting Reports that build themselves from your systems on schedule, with a plain-language summary of what changed.
- Knowledge assistant (RAG) Ask a question in plain words and get an answer from your own documents, with links to the sources.
- Forecasting dashboards Forecast demand from your sales history and seasonality, and flag items to reorder before they run out.
- Payroll automation Turn pay rules, attendance and leave into tested software so the monthly run becomes a review and payslips go out in one batch.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- AI automation and integrations Connect the tools you already use so data moves once, correctly, and AI reads the parts that arrive as text or documents.
Industries
View all industries- Legal Contract review assistants, knowledge search, intake and document automation for law firms and in-house legal teams.
- Logistics and transportation Driver apps, order and shipment tracking, document processing and integrations for logistics and delivery companies.
- Manufacturing Quality inspection, production dashboards, quoting tools, knowledge assistants and legacy system modernization for manufacturers.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
Case studies
View all case studiesGuides and articles
View all guides and articles- How to connect AI to your database safely Let staff ask questions of your data in plain English without risking production systems or sensitive records.
- PostgreSQL vs MySQL The two most popular open-source databases compared for business applications.
- What is RAG and when do you need it? How retrieval-augmented generation lets AI answer from your documents, when it fits and how to build it well.
- How to automate reporting with AI and MCP Build reports that assemble themselves from your systems through MCP, with a written summary people can trust.
- How to set up automated reporting Replace manual weekly and monthly reports with dashboards and summaries that update themselves.
- RAG vs fine-tuning Two ways to make AI work with your knowledge, compared by cost, accuracy and upkeep.
AI models
View all ai models- text-embedding-3-large OpenAI's most capable embedding model for search and retrieval, with 3,072-dimension vectors and support for English and other languages.
- text-embedding-3-small OpenAI's efficient, lowest-cost embedding model, with 1,536-dimension vectors for search, retrieval and similarity at scale.
- Cohere Embed v4 Cohere's multimodal embedding model for enterprise search, embedding text, images and mixed documents, with flexible vector sizes and long inputs.
- Voyage 4 Voyage AI's current embedding series, now part of MongoDB, with large, standard and lite models that share one embedding space.
- Embeddings Models that turn text into vectors for search, retrieval, clustering and recommendations.
- Gemini Embedding 2 Google's current embedding model, multimodal: it embeds text, images, video, audio and PDFs for search and retrieval.
Glossary terms
View all glossary terms- Database A database is an organized store of data that software can search, update and keep consistent, such as customers, orders or bookings.
- RAG RAG, or retrieval-augmented generation, is a method where an AI system first finds relevant passages in your documents, then answers using only those passages.
- Vector database A vector database stores embeddings, lists of numbers that represent meaning, and quickly finds the ones most similar to a query.
- Embeddings Embeddings are lists of numbers that represent the meaning of text or images, so software can find items that are similar in meaning.
- Semantic search Semantic search finds results by meaning rather than exact words, so a search for "reset my login" can find an article titled "Forgot your password".
- Backend The backend is the part of an application that runs on servers, storing data, applying business rules and serving the frontend through APIs.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Yes. It is managed by Snowflake. The older open-source server is deprecated.
Tools defined by your administrator, such as Cortex agents, Cortex Analyst, Cortex Search and SQL.
SQL is read-only by default. Write access must be granted in the server definition.