Overview

Prerequisites

What You Will Learn

What You Will Build

Setup

Create Objects

Programmatic Access Token

Cortex Search Service

Cortex Analyst - Semantic View

Semantic View

Snowflake MCP Server

PREREQUISITE: Successful completion of steps outlined under Setup.

Create Snowflake MCP Server

create or replace mcp server dash_mcp_server from specification
$$
tools:
  - name: "Finance_and_Risk_Assessment_Semantic_View"
    identifier: "DASH_MCP_DB.DATA.FINANCIAL_SERVICES_ANALYTICS"
    type: "CORTEX_ANALYST_MESSAGE"
    description: "Comprehensive semantic model for financial services analytics, providing unified business definitions and relationships across customer data, transactions, marketing campaigns, support interactions, and risk assessments."
    title: "Financial And Risk Assessment"
  - name: "Support_Tickets_Cortex_Search"
    identifier: "DASH_MCP_DB.DATA.SUPPORT_TICKETS"
    type: "CORTEX_SEARCH_SERVICE_QUERY"
    description: "A tool that performs keyword and vector search over unstructured support tickets data."
    title: "Support Tickets Cortex Search"
  - name: "SQL_Execution_Tool"
    type: "SYSTEM_EXECUTE_SQL"
    description: "A tool to execute SQL queries against the connected Snowflake database."
    title: "SQL Execution Tool"
  - name: "Send_Email"
    identifier: "DASH_MCP_DB.DATA.SEND_EMAIL"
    type: "GENERIC"
    description: "A custom tool to send emails to user's verified email address."
    title: "Send_Email"
    config:
      type: "procedure"
      warehouse: "DASH_WH_S"
      input_schema:
        type: "object"
        properties:
          body:
            description: "Use HTML-Syntax for this. If the content you get is in markdown, translate it to HTML. If body is not provided, summarize the last question and use that as content for the email."
            type: "string"
          recipient_email:
            description: "If the email is not provided, send it to the current user's email address."
            type: "string"
          subject:
            description: "If subject is not provided, use Snowflake Intelligence."
            type: "string"
$$;

curl -X POST "https://<YOUR-ORG-YOUR-ACCOUNT>.snowflakecomputing.com/api/v2/databases/dash_mcp_db/schemas/data/mcp-servers/dash_mcp_server" \
  --header 'Content-Type: application/json' \
  --header 'Accept: application/json' \
  --header "Authorization: Bearer <YOUR-PAT-TOKEN>" \
  --data '{
    "jsonrpc": "2.0",
    "id": 12345,
    "method": "tools/list",
    "params": {}
  }'

{
  "jsonrpc" : "2.0",
  "id" : 12345,
  "result" : {
    "tools" : [ {
      "name" : "Finance & Risk Assessment Semantic View",
      "description" : "Comprehensive semantic model for financial services analytics, providing unified business definitions and relationships across customer data, transactions, marketing campaigns, support interactions, and risk assessments.",
      "title" : "Financial And Risk Assessment",
      "inputSchema" : {
        "type" : "object",
        "description" : "A message and additional parameters for Cortex Analyst.",
        "properties" : {
          "message" : {
            "description" : "The user's question.",
            "type" : "string"
          }
        },
        "required" : [ "message" ]
      }
    }, {
      "name" : "Support Tickets Cortex Search",
      "description" : "A tool that performs keyword and vector search over unstructured support tickets data.",
      "title" : "Support Tickets Cortex Search",
      "inputSchema" : {
        "type" : "object",
        "description" : "A search query and additional parameters for search.",
        "properties" : {
          "query" : {
            "description" : "Unstructured text query.",
            "type" : "string"
          },
          "columns" : {
            "description" : "List of columns to return.",
            "type" : "array",
            "items" : {
              "type" : "string"
            }
          },
          "filter" : {
            "description" : "Filter query. Cortex Search supports filtering on the ATTRIBUTES columns specified in the CREATE CORTEX SEARCH SERVICE command.\nCortex Search supports four matching operators:\n1. TEXT or NUMERIC equality: @eq\n2. ARRAY contains: @contains\n3. NUMERIC or DATE/TIMESTAMP greater than or equal to: @gte\n4. NUMERIC or DATE/TIMESTAMP less than or equal to: @lte\nThese matching operators can be composed with various logical operators:\n- @and\n- @or\n- @not\nThe following usage notes apply:\n  Matching against NaN ('not a number') values in the source query are handled as\n  described in Special values. Fixed-point numeric values with more than 19 digits (not\n  including leading zeroes) do not work with @eq, @gte, or @lte and will not be returned\n  by these operators (although they could still be returned by the overall query with the\n  use of @not).\nTIMESTAMP and DATE filters accept values of the form: YYYY-MM-DD and, for timezone\naware dates: YYYY-MM-DD+HH:MM. If the timezone offset is not specified, the date is interpreted in UTC.\nThese operators can be combined into a single filter object.\nExample:\nFiltering on rows where NUMERIC column numeric_col is between 10.5 and 12.5 (inclusive):\n  { \"@and\": [\n    { \"@gte\": { \"numeric_col\": 10.5 } },\n    { \"@lte\": { \"numeric_col\": 12.5 } }\n  ]}\n",
            "type" : "object"
          },
          "limit" : {
            "description" : "Max number of results to return.",
            "type" : "integer",
            "default" : 10
          }
        },
        "required" : [ "query" ]
      }
    }, {
      "name" : "SQL Execution Tool",
      "description" : "A tool to execute SQL queries against the connected Snowflake database.",
      "title" : "SQL Execution Tool",
      "inputSchema" : {
        "type" : "object",
        "description" : "Tool to execute a SQL query.",
        "properties" : {
          "sql" : {
            "description" : "Single SQL query to execute.",
            "type" : "string"
          }
        }
      }
    } ]
  }
}

Cursor

{
    "mcpServers": {
      "Snowflake MCP Server": {
        "url": "https://<YOUR-ORG-YOUR-ACCOUNT>.snowflakecomputing.com/api/v2/databases/dash_mcp_db/schemas/data/mcp-servers/dash_mcp_server",
            "headers": {
              "Authorization": "Bearer <YOUR-PAT-TOKEN>"
            }
      }
    }
}

Q&A in Cursor

Q1. Show me the results for risk profile distribution across customer segments with transaction volumes. Include the number of customers, transaction counts, and average transactions per customer for each segment and risk profile combination.

Q2. What is the average customer lifetime value by region for customers with Low risk profile?

Q3. What is the risk profile distribution across customer segments and their correlation with transaction volumes?

Q4. Can you summarize the overall sentiments based on the support calls?

Q5. Which support categories would benefit most from automated responses based on transcript analysis?

Custom Tools

Send me an email with a summary of the analysis to YOUR-EMAIL-ADDRESS.

NOTE: You may also use an existing agent that you have access to.

create or replace mcp server dash_mcp_server from specification
$$
tools:
  - name: "Finance_and_Risk_Assessment_Semantic_View"
    identifier: "DASH_MCP_DB.DATA.FINANCIAL_SERVICES_ANALYTICS"
    type: "CORTEX_ANALYST_MESSAGE"
    description: "Comprehensive semantic model for financial services analytics, providing unified business definitions and relationships across customer data, transactions, marketing campaigns, support interactions, and risk assessments."
    title: "Financial And Risk Assessment"
  - name: "Support_Tickets_Cortex_Search"
    identifier: "DASH_MCP_DB.DATA.SUPPORT_TICKETS"
    type: "CORTEX_SEARCH_SERVICE_QUERY"
    description: "A tool that performs keyword and vector search over unstructured support tickets data."
    title: "Support Tickets Cortex Search"
  - name: "SQL_Execution_Tool"
    type: "SYSTEM_EXECUTE_SQL"
    description: "A tool to execute SQL queries against the connected Snowflake account."
    title: "SQL Execution Tool"
  - name: "Snowflake_Documentation_Agent"
    identifier: "SNOWFLAKE_INTELLIGENCE.AGENTS.SNOWFLAKE_DOCUMENTATION"
    type: "CORTEX_AGENT_RUN"
    description: "An agent that performs keyword and vector search over Snowflake Documentation."
    title: "Snowflake Documentation"
  - name: "Send_Email"
    identifier: "DASH_MCP_DB.DATA.SEND_EMAIL"
    type: "GENERIC"
    description: "A custom tool to send emails to user's verified email address."
    title: "Send_Email"
    config:
      type: "procedure"
      warehouse: "DASH_WH_S"
      input_schema:
        type: "object"
        properties:
          body:
            description: "Use HTML-Syntax for this. If the content you get is in markdown, translate it to HTML. If body is not provided, summarize the last question and use that as content for the email."
            type: "string"
          recipient_email:
            description: "If the email is not provided, send it to the current user's email address."
            type: "string"
          subject:
            description: "If subject is not provided, use Snowflake Intelligence."
            type: "string"
$$;

Q1. How do I create an agent?

Q2. What are virtual warehouses in Snowflake, and how do I properly size them?

Conclusion And Resources

What You Learned

Related Resources