Serveur MCP géré par Snowflake¶

Vue d’ensemble¶

Le Model Context Protocol (MCP) est une norme open source qui permet aux agents AI d’interagir en toute sécurité avec les applications métier et les systèmes de données externes, tels que les bases de données et les référentiels de contenu. Le MCP permet aux entreprises de réduire les défis d’intégration et de produire rapidement des résultats à partir de modèles. Depuis son lancement, le MCP est devenu essentiel pour les applications agentiques, fournissant un dispositif cohérent et sécurisé pour l’appel d’outils et la récupération de données.

The Snowflake-managed MCP server lets AI agents securely retrieve data from Snowflake accounts without needing to deploy separate infrastructure. You can configure the MCP server to serve Cortex Analyst, Cortex Search, and Cortex Agents as tools, along with custom tools and SQL executions on the standards-based interface. MCP clients discover and invoke these tools, and retrieve data required for the application. With managed MCP servers on Snowflake, you can build scalable enterprise-grade applications while maintaining access and privacy controls. The MCP server on Snowflake provides:

• Intégration standard : interface unifiée pour la détection et l’appel d’outils, conformément aux normes en constante évolution.

• Authentification complète : service OAuth intégré de Snowflake pour activer l’authentification basée sur OAuth pour les intégrations MCP.

• Gouvernance robuste : contrôle d’accès basé sur les rôles (RBAC) pour le serveur MCP et les outils pour gérer la détection et l’appel d’outils.

Pour plus d’informations sur le cycle de vie MCP, voir Cycle de vie. Pour un exemple d’une mise en œuvre MCP, voir le guide de démarrage rapide Premiers pas avec le serveur MCP Snowflake géré.

MCP server security recommendations¶

Using multiple MCP servers without verifying tools and descriptions could lead to vulnerabilities such as tool poisoning or tool shadowing. Snowflake recommends verifying third-party MCP servers before using them. This includes any MCP server from another Snowflake user or account. Verify all tools offered by third-party MCP servers.

We recommend using OAuth as the authentication method. Using hardcoded tokens can lead to token leakage.

When using a Programmatic Access Token (PAT), set it to use the least-privileged role allowed to work with MCP. This will help prevent leaking a secret with access to a highly-privileged role.

Configure proper permissions for the MCP server and tools following the least-privilege principle. Access to the MCP Server does not give access to the tools. Permission needs to be granted for each tool.

Créer un objet du serveur MCP¶

Créez un objet, en spécifiant les outils et les autres métadonnées. Les clients MCP qui se connectent au serveur sont en mesure de détecter et d’appeler ces outils après l’authentification requise.

1. Accédez à la base de données et au schéma de votre choix pour créer le serveur MCP.

2. Créer le serveur MCP :

   CREATE [ OR REPLACE ] MCP SERVER [ IF NOT EXISTS ] <server_name>
     FROM SPECIFICATION $$
       tools:
         - name: "product-search"
           type: "CORTEX_SEARCH_SERVICE_QUERY"
           identifier: "database1.schema1.Cortex_Search_Service1"
           description: "cortex search service for all products"
           title: "Product Search"
   
         - name: "revenue-semantic-view"
           type: "CORTEX_ANALYST_MESSAGE"
           identifier: "database1.schema1.Semantic_View_1"
           description: "Semantic view for all revenue tables"
           title: "Semantic view for revenue"
     $$
   

   Copy

Snowflake prend actuellement en charge les types d’outils suivants :

• CORTEX_SEARCH_SERVICE_QUERY: outil Cortex Search Service

• CORTEX_ANALYST_MESSAGE: outil Cortex Analyst

• SYSTEM_EXECUTE_SQL: SQL execution

• CORTEX_AGENT_RUN: Cortex Agent tool

• GENERIC: tool for UDFs and stored procedures

The following examples show how to configure different tool types:

Analyst toolSearch toolSQL execution toolAgent toolCustom tool

Using the Analyst tool, your client can generate text from SQL. Use the following code to specify the tool configuration.

Note

The Snowflake-managed MCP server only supports using semantic views with Cortex Analyst. It does not support semantic models.

tools:
  - name: "revenue-semantic-view"
    type: "CORTEX_ANALYST_MESSAGE"
    identifier: "database1.schema1.Semantic_View_1"
    description: "Semantic view for all revenue tables"
    title: "Semantic view for revenue"

Copy

Use the following examples to create and configure custom tools using UDFs and stored procedures:

-- create a simple udf
CREATE OR REPLACE FUNCTION MULTIPLY_BY_TEN(x FLOAT)
RETURNS FLOAT
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
HANDLER = 'multiply_by_ten'
AS
$$
def multiply_by_ten(x: float) -> float:
  return x * 10
$$;

SHOW FUNCTIONS LIKE 'MULTIPLY_BY_TEN';

-- test return json/variant
CREATE OR REPLACE FUNCTION CALCULATE_PRODUCT_AND_SUM(x FLOAT, y FLOAT)
RETURNS VARIANT
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
HANDLER = 'calculate_values'
AS
$$
import json

def calculate_values(x: float, y: float) -> dict:
  """
  Calculates the product and sum of two numbers and returns them in a dictionary.
  The dictionary is converted to a VARIANT (JSON) in the SQL return.
  """
  product = x * y
  sum_val = x + y

  return {
      "product": product,
      "sum": sum_val
  }
$$;

-- test return list/array
CREATE OR REPLACE FUNCTION GET_NUMBERS_IN_RANGE(x FLOAT, y FLOAT)
RETURNS ARRAY -- Use ARRAY to explicitly state a list is being returned
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
HANDLER = 'get_numbers'
AS
$$
def get_numbers(x: float, y: float) -> list:
  """
  Returns a list of integers between x (exclusive) and y (inclusive).
  Assumes x < y.
  """
  # Ensure x and y are treated as integers for range generation
  start = int(x) + 1
  end = int(y) + 1 # range() is exclusive on the stop value

  # Use a list comprehension to generate the numbers
  # The Python list will be converted to a Snowflake ARRAY.
  return list(range(start, end))
$$;

-- create a simple stored procedure
CREATE OR REPLACE PROCEDURE MULTIPLY_BY_TEN_SP(x FLOAT)
RETURNS FLOAT
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
PACKAGES = ('snowflake-snowpark-python')
HANDLER = 'multiply_by_ten'
AS
$$
# The handler logic is identical to the UDF for a scalar return
def multiply_by_ten(x: float) -> float:
      return x * 10
$$;

-- test return json/variant
CREATE OR REPLACE PROCEDURE CALCULATE_VALUES_SP(x FLOAT, y FLOAT)
RETURNS VARIANT
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
PACKAGES = ('snowflake-snowpark-python')
HANDLER = 'calculate_values'
AS
$$
# The handler logic is identical to the UDF for a VARIANT return
def calculate_values(x: float, y: float) -> dict:
      """
      Calculates the product and sum of two numbers and returns them in a dictionary.
      The dictionary is converted to a VARIANT (JSON) in the SQL return.
      """
      product = x * y
      sum_val = x + y

      return {
          "product": product,
          "sum": sum_val
      }
$$;

-- test return list/array
CREATE OR REPLACE PROCEDURE GET_NUMBERS_SP(x FLOAT, y FLOAT)
RETURNS ARRAY
LANGUAGE PYTHON
RUNTIME_VERSION = '3.8'
PACKAGES = ('snowflake-snowpark-python')
HANDLER = 'get_numbers'
AS
$$
def get_numbers(x: float, y: float) -> list:
      """
      Returns a list of integers between x (exclusive) and y (inclusive).
      The Python list will be converted to a Snowflake ARRAY.
      """
      # Ensure x and y are treated as integers for range generation
      start = int(x) + 1
      end = int(y) + 1 # range() is exclusive on the stop value

      # Use a list comprehension to generate the numbers
      return list(range(start, end))
$$;

CREATE MCP SERVER my_mcp_server
  FROM SPECIFICATION $$
    tools:
      - title: "Custom Tool 1"
        identifier: "EXAMPLE_DATABASE.AGENTS.MULTIPLY_BY_TEN"
        name: "multiply_by_ten"
        type: "GENERIC"
        description: "Multiplied input value by ten and returns the result."
        config:
          type: "function"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "A number to be multiplied by ten"
                type: "number"
      - title: "Custom Tool 2"
        identifier: "EXAMPLE_DATABASE.AGENTS.CALCULATE_PRODUCT_AND_SUM"
        name: "calculate_product_and_sum"
        type: "GENERIC"
        description: "Calculates the product and sum of two numbers and returns them in a JSON object."
        config:
          type: "function"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "First number"
                type: "number"
              y:
                description: "Second number"
                type: "number"
      - title: "Custom Tool 3"
        identifier: "EXAMPLE_DATABASE.AGENTS.GET_NUMBERS_IN_RANGE"
        name: "get_numbers_in_range"
        type: "GENERIC"
        description: "Returns a list of integers between two numbers."
        config:
          type: "function"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "Start number (exclusive)"
                type: "number"
              y:
                description: "End number (inclusive)"
                type: "number"
      - title: "Custom Tool 4"
        identifier: "EXAMPLE_DATABASE.AGENTS.MULTIPLY_BY_TEN_SP"
        name: "multiply_by_ten_sp"
        type: "GENERIC"
        description: "Multiplied input value by ten and returns the result."
        config:
          type: "procedure"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "A number to be multiplied by ten"
                type: "number"
      - title: "Custom Tool 5"
        identifier: "EXAMPLE_DATABASE.AGENTS.CALCULATE_PRODUCT_AND_SUM_SP"
        name: "calculate_product_and_sum_sp"
        type: "GENERIC"
        description: "Calculates the product and sum of two numbers and returns them in a JSON object."
        config:
          type: "procedure"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "First number"
                type: "number"
              y:
                description: "Second number"
                type: "number"
      - title: "Custom Tool 6"
        identifier: "EXAMPLE_DATABASE.AGENTS.GET_NUMBERS_IN_RANGE_SP"
        name: "get_numbers_in_range_sp"
        type: "GENERIC"
        description: "Returns a list of integers between two numbers."
        config:
          type: "procedure"
          warehouse: "COMPUTE_SERVICE_WAREHOUSE"
          input_schema:
            type: "object"
            properties:
              x:
                description: "Start number (exclusive)"
                type: "number"
              y:
                description: "End number (inclusive)"
                type: "number"
  $$;

1. Pour afficher les serveurs MCP, utilisez les commandes suivantes :

   SHOW MCP SERVERS IN DATABASE <database_name>;
   SHOW MCP SERVERS IN SCHEMA <schema_name>;
   SHOW MCP SERVERS IN ACCOUNT;
   

   Copy

   The following shows the output of the command:

   |               created_on               |       name        | database_name | schema_name |    owner     |           comment            |
   ------------------------------------------+-------------------+---------------+-------------+--------------+------------------------------
   | Fri, 23 Jun 1967 07:00:00.123000 +0000 | TEST_MCP_SERVER   | TEST_DATABASE | TEST_SCHEMA | ACCOUNTADMIN | [NULL]                       |
   | Fri, 23 Jun 1967 07:00:00.123000 +0000 | TEST_MCP_SERVER_2 | TEST_DATABASE | TEST_SCHEMA | ACCOUNTADMIN | Test MCP server with comment |
   

2. Pour décrire un serveur MCP, utilisez la commande suivante :

   DESCRIBE MCP SERVER <server_name>;
   

   Copy

   The following shows the output of the command:

   |      name       | database_name | schema_name |    owner     | comment |     server_spec        |               created_on               |
   ------------------------------------------------------------------------------------------------------+-------------------------------------
   | TEST_MCP_SERVER | TEST_DATABASE | TEST_SCHEMA | ACCOUNTADMIN | [NULL]  | {"version":1,"tools":[{"name":"product-search","identifier":"db.schema.search_service","type":"CORTEX_SEARCH_SERVICE_QUERY"}]} | Fri, 23 Jun 1967 07:00:00.123000 +0000 |
   

3. Pour abandonner un serveur MCP, utilisez la commande suivante :

   DROP MCP SERVER <server_name>;
   

   Copy

Contrôle d’accès¶

Vous pouvez utiliser les privilèges suivants pour gérer l’accès à l’objet MCP et aux outils sous-jacents

Configurer l’authentification OAuth¶

Configuration de l’authentification sur le client MCP. Le serveur MCP géré par Snowflake prend en charge l’authentification 2.0 OAuth alignée avec la recommandation d’autorisation dans le protocole MCP. Le serveur MCP géré par Snowflake ne prend pas en charge l’enregistrement dynamique des clients.

1. Tout d’abord, créez l’intégration de sécurité. Pour plus d’informations sur cette commande, voir CREATE SECURITY INTEGRATION (Snowflake OAuth).

   CREATE [ OR REPLACE ] SECURITY INTEGRATION [IF NOT EXISTS] <integration_name>
     TYPE = OAUTH
     OAUTH_CLIENT = GENERIC
     ENABLED = TRUE
     OAUTH_CLIENT_TYPE = 'CONFIDENTIAL'
     OAUTH_REDIRECT_URI = '<redirect_URI>'
   

   Copy

2. Ensuite, appelez la fonction système pour récupérer votre identifiant client et les clés pour la configuration du client. Le nom de l’intégration est sensible à la casse et doit être en majuscules.

   SELECT SYSTEM$SHOW_OAUTH_CLIENT_SECRETS('<integration_name>');
   

   Copy

Interagir avec le serveur MCP à l’aide d’un client MCP personnalisé¶

Si vous créez un client MCP personnalisé, les sections suivantes présentent les points de terminaison Snowflake avec lesquels votre client interagit.

POST /api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}
    {
        "jsonrpc": "2.0",
        "id": 1,
        "method": "initialize",
        "params": { "protocolVersion": "2025-06-18" }
    }

{
    "jsonrpc": "2.0", // passthrough from req
    "id": 1, // passthrough from req
    "result": {
        "proto_version": "2025-06-18",
        "capabilities": {
            "tools": {
                "listChanged": false
            }
        },
        "server_info": {
            "name": "<snowflake-mcp-name>",
            "title": "Snowflake Server: <snowflake-mcp-name>",
            "version": "1.0.0"
        }
    }
}

POST /api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}
    {
        "jsonrpc": "2.0",
        "id": 1,
        "method": "tools/list",
        "params": {}
    }

{
    "jsonrpc": "2.0", // passthrough from req
    "id": 1, // passthrough from req
    "result": {
        "tools": [ // search
            {
                "name":"product-search",
                "description":"Test search tool",
                "inputSchema": {
                    "type": "object",
                    "description": "A search query and additional parameters for search.",
                    "properties": {
                        "query": {
                            "description": "Unstructured text query.  Exactly one of 'query' or 'multi_index_query' must be specified.",
                            "type": "string"
                        },
                        "columns": {
                            "description": "List of columns to return.",
                            "type": "array",
                            "items": {
                                "type": "string"
                            }
                        },
                        "filter": {
                            "description": "Filter query.",
                            "type": "object"
                        },
                        "limit": {
                            "description": "Max number of results to return.",
                            "type": "integer",
                            "default": 10
                        }
                    }
                },
                "outputSchema": {
                    "type": "object",
                    "description": "Search results.",
                    "properties": {
                        "results": {
                            "description": "List of result rows.",
                            "type": "array",
                            "items": {
                                "type": "object",
                                "additionalProperties": true,
                                "description": "Map of column names to values (as bytes)."
                            }
                        },
                    "request_id": {
                        "description": "ID of the request.",
                        "type": "string"
                    }
                },
                "required": ["results", "request_id"]
            }
          },
          { // analyst
              "name":"revenue-semantic-view",
              "description":"Test tool",
              "inputSchema": {
                  "type": "object",
                  "description": "A message and additional parameters for Cortex Analyst.",
                  "properties": {
                      "message": {
                          "description": "The user’s question.",
                          "type": "string"
                      }
                  }
              }
          }
        ]
    }
}

POST /api/v2/databases/<database>/schemas/<schema>/mcp-servers/<name>
    {
        "jsonrpc": "2.0",
        "id": 1,
        "method": "tools/call",
        "params": {
            "name": "test-analyst",
            "arguments": {
                "message ": "text"
            }
        }
    }

{
    "jsonrpc": "2.0",
    "id": 1,
    "result": {
        "content": [
            {
                "type": "text",
                "text": "string"
            }
        ]
    }
}

POST /api/v2/databases/{database}/schemas/{schema}/mcp-servers/{name}
    {
        "jsonrpc": "2.0",
        "id": 1,
        "method": "tools/call",
        "params": {
            "name": "product-search",
            "arguments": {
                "query": "Hotels in NYC",
                "columns": array of strings,
                "filter": json,
                "limit": int
            }
        }
  }

{
    "jsonrpc": "2.0",
    "id": 1,
    "result": {
        "results": {}
    }
}

Limitations¶

Le serveur MCP géré par Snowflake ne prend pas en charge les constructions suivantes dans le protocole MCP : ressources, invites, racines, notifications, négociations de version, phases de cycle de vie et échantillonnage.

Seules les réponses sans flux sont prises en charge.