snowflake-mcp-server
❄️ snowflake-mcp-server
使用原生 Snowflake Data Cloud 与 Cortex AI 超级能力,为 AI 智能体强力赋能! ⚡
一个企业级 Model Context Protocol (MCP) 服务器,提供横跨 18 个领域模块的 127 个工具,支持零配置连接解析、安全的 SQL 执行、虚拟仓库管理、对象检查以及 Cortex AI 集成,可直接接入您最喜爱的 AI 助手。
🛡️ 企业免责声明与安全
[!IMPORTANT] 社区项目免责声明
snowflake-mcp-server是一个依据 Apache 2.0 许可证发布的独立开源项目,与 Snowflake Inc. 没有关联,也不受其赞助、背书或支持。"Snowflake" 与 "Cortex" 是 Snowflake Inc. 的商标。
[!WARNING] 安全护栏
只读安全模式: 设置
SNOWFLAKE_MCP_READONLY=1(或传入--readonly)以禁用所有 DDL/DML 变更能力。破坏性操作安全闸门: 删除数据库、架构或表需要显式传入
confirm=True。查询限制: 默认执行限制可防止上下文窗口溢出(
SNOWFLAKE_MAX_ROWS=1000、SNOWFLAKE_QUERY_TIMEOUT=120)。
Related MCP server: Snowflake MCP Server
🔌 连接与多种认证方式解析
snowflake-mcp-server 可自动解析所有企业级 Snowflake 配置中的凭据:
Snowflake CLI 继承(
~/.snowflake/connections.toml): 零配置连接。如果您已通过snow配置了连接,服务器会自动连接到您的默认或指定配置文件(-c <conn_name>)。编程访问令牌 (PAT) / OAuth: 在连接配置文件中设置
token,或设置SNOWFLAKE_TOKEN。RSA 密钥对 JWT 认证: 设置
SNOWFLAKE_PRIVATE_KEY_PATH(以及可选的SNOWFLAKE_PRIVATE_KEY_PASSPHRASE)。SSO / 浏览器认证: 设置
SNOWFLAKE_AUTHENTICATOR=externalbrowser。环境变量: 标准
SNOWFLAKE_ACCOUNT、SNOWFLAKE_USER、SNOWFLAKE_PASSWORD、SNOWFLAKE_WAREHOUSE、SNOWFLAKE_DATABASE、SNOWFLAKE_SCHEMA、SNOWFLAKE_ROLE。
📦 安装与快速开始
# Install via pip
pip install snowflake-mcp-server
# Run with a specific Snowflake CLI connection profile
snowflake-mcp -c my_connection
# Run in read-only mode
snowflake-mcp -c my_connection --readonly
# Run with Docker
docker build -t snowflake-mcp-server .
docker run -i --rm snowflake-mcp-server🛠️ 完整工具套件(127 个企业级工具)
领域套件 | 数量 | 关键工具 |
1. SQL 查询与事务 | 8 |
|
2. 数据库与克隆 | 7 |
|
3. 架构与克隆 | 6 |
|
4. 表、视图与分区 | 10 |
|
5. 虚拟仓库与扩缩容 | 8 |
|
6. Stage 与文件操作 | 6 |
|
7. 任务与 DAG 管道 | 7 |
|
8. Stream 与变更数据捕获 | 5 |
|
9. 动态表与 Iceberg 表 | 7 |
|
10. Snowpipe 与数据摄取 | 5 |
|
11. 警报与通知 | 6 |
|
12. 治理、RBAC 与用户 | 10 |
|
13. 网络与密码策略 | 6 |
|
14. SPCS 计算池与 Streamlit | 8 |
|
15. 对象标签与分类 | 4 |
|
16. 可编程性、UDF 与 Secret | 8 |
|
17. Cortex AI 与 NLP 扩展 | 8 |
|
18. 复合智能体工作流 | 8 |
|
📜 许可证
Apache 2.0。版权所有 (c) 2026 Christian Claudio。
Available Tools
140 toolsalerts_create_alertAlerts Create AlertB
Create an alert with schedule, condition SQL, and action SQL. Destructive actions require confirm=True.
Inputs: schedule (required), action_sql (required), alert_name (required), condition_sql (required), +5 more. Returns: object
alerts_describe_alertAlerts Describe AlertBRead-onlyIdempotent
Describe alert condition SQL, action SQL, schedule, and warehouse.
Inputs: alert_name (required), database, schema_name. Returns: object
alerts_drop_alertAlerts Drop AlertADestructive
Drop an alert in Snowflake. Requires confirmation.
Inputs: alert_name (required), confirm, database, schema_name. Returns: object
alerts_list_alertsAlerts List AlertsBRead-onlyIdempotent
List configured alerts with condition queries, schedules, and state. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
alerts_resume_alertAlerts Resume AlertCIdempotent
Resume a suspended alert.
Inputs: alert_name (required), database, schema_name. Returns: object
alerts_suspend_alertAlerts Suspend AlertBIdempotent
Suspend an active alert.
Inputs: alert_name (required), database, schema_name. Returns: object
compute_services_describe_compute_poolCompute Services Describe Compute PoolBRead-onlyIdempotent
Describe compute pool instance family, min/max nodes, active nodes, and state.
Inputs: pool_name (required). Returns: object
compute_services_describe_streamlitCompute Services Describe StreamlitARead-onlyIdempotent
Describe Streamlit application root location, stage, and query warehouse.
Inputs: streamlit_name (required), database, schema_name. Returns: object
compute_services_list_compute_poolsCompute Services List Compute PoolsBRead-onlyIdempotent
List Snowpark Container Services (SPCS) compute pools. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
compute_services_list_image_repositoriesCompute Services List Image RepositoriesBRead-onlyIdempotent
List OCI image repositories in Snowflake. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
compute_services_list_servicesCompute Services List ServicesBRead-onlyIdempotent
List container services running on SPCS compute pools. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
compute_services_list_streamlitsCompute Services List StreamlitsBRead-onlyIdempotent
List Streamlit applications hosted in Snowflake. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
compute_services_resume_compute_poolCompute Services Resume Compute PoolAIdempotent
Resume an idle or suspended SPCS compute pool.
Inputs: pool_name (required). Returns: object
compute_services_suspend_compute_poolCompute Services Suspend Compute PoolAIdempotent
Suspend an active SPCS compute pool to stop node provisioning costs.
Inputs: pool_name (required). Returns: object
cortex_analyst_queryCortex Analyst QueryBRead-onlyIdempotent
Answer an analytical question via AI_COMPLETE. Optionally prefixes the prompt with semantic_model_path. Does not call Cortex Analyst REST (POST /api/v2/cortex/analyst/message).
Inputs: question (required), semantic_model_path. Returns: object
cortex_completeCortex CompleteARead-onlyIdempotent
Run LLM completion via Snowflake AI_COMPLETE (e.g., 'llama3.3-70b', 'llama3.1-8b'). Optional temperature (0 to 1) and max_tokens are sent as model_parameters only when set; with neither set the call stays AI_COMPLETE(model, prompt) and still returns a string.
Inputs: prompt (required), model, max_tokens, temperature. Returns: object
cortex_embed_text_768Cortex Embed Text 768ARead-onlyIdempotent
Generate text embeddings via Snowflake AI_EMBED. Output dimension is set by the model (default snowflake-arctic-embed-m is 768); replaces legacy EMBED_TEXT_768.
Inputs: text (required), model. Returns: object
cortex_extract_answerCortex Extract AnswerBRead-onlyIdempotent
Extract answers from text via Snowflake AI_EXTRACT. Returns the AI_EXTRACT JSON object (response/error), not a legacy plain-string answer.
Inputs: question (required), source_text (required). Returns: object
cortex_searchCortex SearchCRead-onlyIdempotent
Query a Snowflake Cortex Search Service index over unstructured text.
Inputs: query (required), service_name (required), limit, columns. Returns: object
cortex_sentimentCortex SentimentARead-onlyIdempotent
Analyze sentiment via Snowflake AI_SENTIMENT. Returns an object with a categories array (overall plus optional aspects), not a legacy -1.0..1.0 float score.
Inputs: text (required). Returns: object
cortex_summarizeCortex SummarizeBRead-onlyIdempotent
Summarize text via Snowflake AI_SUMMARIZE (drop-in for legacy CORTEX.SUMMARIZE).
Inputs: text (required). Returns: object
cortex_translateCortex TranslateBRead-onlyIdempotent
Translate text via Snowflake AI_TRANSLATE (drop-in for legacy CORTEX.TRANSLATE).
Inputs: text (required), source_language (required), target_language (required). Returns: object
databases_clone_databaseDatabases Clone DatabaseB
Create a zero-copy clone of a database in Snowflake.
Inputs: source_database (required), target_database (required). Returns: object
databases_create_databaseDatabases Create DatabaseC
Create a new database in Snowflake.
Inputs: name (required), comment, if_not_exists, data_retention_time_in_days. Returns: object
databases_describe_databaseDatabases Describe DatabaseBRead-onlyIdempotent
Describe properties, owner, retention time, and comment of a database.
Inputs: database_name (required). Returns: object
databases_drop_databaseDatabases Drop DatabaseADestructive
Drop a database in Snowflake. Requires confirmation flag.
Inputs: name (required), confirm. Returns: object
databases_get_database_ddlDatabases Get Database DdlBRead-onlyIdempotent
Retrieve the exact CREATE DATABASE DDL definition.
Inputs: database_name (required). Returns: object
databases_list_databasesDatabases List DatabasesCRead-onlyIdempotent
List all available databases accessible to the current role. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
databases_undrop_databaseDatabases Undrop DatabaseA
Restore a recently dropped database using Time Travel.
Inputs: name (required). Returns: object
dynamic_tables_describe_dynamic_tableDynamic Tables Describe Dynamic TableARead-onlyIdempotent
Describe dynamic table definition, target lag, warehouse, and query text.
Inputs: table_name (required), database, schema_name. Returns: object
dynamic_tables_describe_iceberg_tableDynamic Tables Describe Iceberg TableBRead-onlyIdempotent
Describe schema, catalog integration, and external volume of an Iceberg table.
Inputs: table_name (required), database, schema_name. Returns: object
dynamic_tables_list_catalog_integrationsDynamic Tables List Catalog IntegrationsARead-onlyIdempotent
List catalog integrations (Polaris, AWS Glue, Object Storage) configured in Snowflake. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
dynamic_tables_list_dynamic_tablesDynamic Tables List Dynamic TablesCRead-onlyIdempotent
List dynamic tables with lag targets, refresh mode, and last refresh status. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
dynamic_tables_list_external_volumesDynamic Tables List External VolumesBRead-onlyIdempotent
List external cloud storage volumes configured for Apache Iceberg tables. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
dynamic_tables_list_iceberg_tablesDynamic Tables List Iceberg TablesBRead-onlyIdempotent
List Apache Iceberg tables in the account, database, or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
dynamic_tables_refresh_dynamic_tableDynamic Tables Refresh Dynamic TableBIdempotent
Trigger an immediate manual refresh of a dynamic table.
Inputs: table_name (required), database, schema_name. Returns: object
dynamic_tables_resume_dynamic_tableDynamic Tables Resume Dynamic TableCIdempotent
Resume scheduling and lag monitoring for a dynamic table.
Inputs: table_name (required), database, schema_name. Returns: object
dynamic_tables_suspend_dynamic_tableDynamic Tables Suspend Dynamic TableBIdempotent
Suspend automated refresh and lag evaluation for a dynamic table.
Inputs: table_name (required), database, schema_name. Returns: object
governance_create_roleGovernance Create RoleC
Create a new role in Snowflake.
Inputs: role_name (required), comment, if_not_exists. Returns: object
governance_create_userGovernance Create UserC
Create a new Snowflake user with default role and warehouse.
Inputs: user_name (required), comment, password, default_role, +2 more. Returns: object
governance_describe_roleGovernance Describe RoleARead-onlyIdempotent
Describe role properties and assigned grants. A name in double quotes, such as a list row's quoted_name, must match exactly.
Inputs: role_name (required). Returns: object
governance_describe_userGovernance Describe UserARead-onlyIdempotent
Describe user properties, email, disabled status, and default warehouse/role.
Inputs: user_name (required). Returns: object
governance_drop_roleGovernance Drop RoleBDestructive
Drop a role in Snowflake. Requires confirmation.
Inputs: role_name (required), confirm. Returns: object
governance_get_current_contextGovernance Get Current ContextARead-onlyIdempotent
Retrieve current active session context (current user, role, warehouse, database, schema, and account).
Inputs: no named parameters. Returns: object
governance_list_connectionsGovernance List ConnectionsARead-onlyIdempotent
List available connection profiles configured in ~/.snowflake/connections.toml and show active profile.
Inputs: no named parameters. Returns: object
governance_list_grants_to_roleGovernance List Grants To RoleARead-onlyIdempotent
List privileges granted to a specific role.
Inputs: role_name (required). Returns: object
governance_list_grants_to_userGovernance List Grants To UserBRead-onlyIdempotent
List roles granted to a specific user.
Inputs: user_name (required). Returns: object
governance_list_rolesGovernance List RolesCRead-onlyIdempotent
List roles available in the Snowflake account. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
governance_list_usersGovernance List UsersBRead-onlyIdempotent
List users in the Snowflake account with login status and default roles. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
governance_use_connectionGovernance Use ConnectionBIdempotent
Dynamically switch the active Snowflake session to a different connection profile from ~/.snowflake/connections.toml.
Inputs: connection_name (required). Returns: object
horizon_describe_masking_policyHorizon Describe Masking PolicyBRead-onlyIdempotent
Describe signature, return type, and body of a masking policy.
Inputs: policy_name (required), database, schema_name. Returns: object
horizon_describe_row_access_policyHorizon Describe Row Access PolicyBRead-onlyIdempotent
Describe signature, filter expression, and comment of a row access policy.
Inputs: policy_name (required), database, schema_name. Returns: object
horizon_get_column_lineageHorizon Get Column LineageARead-onlyIdempotent
Trace origin and transformation lineage for one column from SNOWFLAKE.ACCOUNT_USAGE.ACCESS_HISTORY (direct objects, base objects, and objects modified, including baseSources and directSources). The view lags up to 3 hours and requires Enterprise Edition (or higher).
Inputs: table_name (required), column_name (required), days, limit, +2 more. Returns: object
horizon_get_object_lineageHorizon Get Object LineageBRead-onlyIdempotent
Retrieve upstream source and downstream dependent object lineage from Snowflake Horizon.
Inputs: object_name (required), database, direction, schema_name. Returns: object
horizon_list_masking_policiesHorizon List Masking PoliciesBRead-onlyIdempotent
List column masking policies in the account, database, or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
horizon_list_row_access_policiesHorizon List Row Access PoliciesARead-onlyIdempotent
List row access policies defined in the account, database, or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
network_describe_network_policyNetwork Describe Network PolicyBRead-onlyIdempotent
Describe allowed IP lists, blocked IP lists, and comments for a network policy.
Inputs: policy_name (required). Returns: object
network_describe_network_ruleNetwork Describe Network RuleBRead-onlyIdempotent
Describe mode (INGRESS, INTERNAL_STAGE, EGRESS), type (IPV4, AWSVPCEID, HOST_PORT), and value list of a network rule.
Inputs: rule_name (required), database, schema_name. Returns: object
network_describe_password_policyNetwork Describe Password PolicyBRead-onlyIdempotent
Describe password policy constraints (min length, lockout time, history, age).
Inputs: policy_name (required), database, schema_name. Returns: object
network_list_network_policiesNetwork List Network PoliciesBRead-onlyIdempotent
List network policies configured in the account. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
network_list_network_rulesNetwork List Network RulesBRead-onlyIdempotent
List network rules defined in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
network_list_password_policiesNetwork List Password PoliciesBRead-onlyIdempotent
List password security policies defined in the account or database. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
pipes_create_pipePipes Create PipeC
Create a Snowpipe for continuous ingestion.
Inputs: pipe_name (required), copy_statement (required), database, auto_ingest, +2 more. Returns: object
pipes_describe_pipePipes Describe PipeCRead-onlyIdempotent
Describe pipe definition and COPY statement.
Inputs: pipe_name (required), database, schema_name. Returns: object
pipes_drop_pipePipes Drop PipeBDestructive
Drop a Snowpipe. Requires confirmation.
Inputs: pipe_name (required), confirm, database, schema_name. Returns: object
pipes_get_pipe_statusPipes Get Pipe StatusARead-onlyIdempotent
Get execution and health status of a Snowpipe (pending file count, last ingested timestamp).
Inputs: pipe_name (required), database, schema_name. Returns: object
pipes_list_pipesPipes List PipesBRead-onlyIdempotent
List Snowpipes configured in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
programmability_describe_functionProgrammability Describe FunctionBRead-onlyIdempotent
Describe UDF function signature, return type, language, and body.
Inputs: function_signature (required), database, schema_name. Returns: object
programmability_describe_procedureProgrammability Describe ProcedureARead-onlyIdempotent
Describe procedure signature, return type, language, and definition body.
Inputs: procedure_signature (required), database, schema_name. Returns: object
programmability_describe_secretProgrammability Describe SecretARead-onlyIdempotent
Describe secret metadata, type (GENERIC_STRING, OAUTH2), and owner without exposing secret value.
Inputs: secret_name (required), database, schema_name. Returns: object
programmability_list_event_tablesProgrammability List Event TablesBRead-onlyIdempotent
List event tables used for application logging, tracing, and SPCS telemetry. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
programmability_list_functionsProgrammability List FunctionsBRead-onlyIdempotent
List user-defined functions (UDFs) in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
programmability_list_integrationsProgrammability List IntegrationsBRead-onlyIdempotent
List external integrations (API, Storage, Notification, Security integrations). Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, integration_type. Returns: object
programmability_list_notification_integrationsProgrammability List Notification IntegrationsCRead-onlyIdempotent
List notification integrations configured for alerts, tasks, and cloud messaging (SNS, PubSub, Webhooks). Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
programmability_list_proceduresProgrammability List ProceduresCRead-onlyIdempotent
List stored procedures in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
programmability_list_secretsProgrammability List SecretsBRead-onlyIdempotent
List security secrets (API keys, OAuth credentials) stored in Snowflake. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
programmability_list_sequencesProgrammability List SequencesBRead-onlyIdempotent
List auto-increment sequences in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
queries_begin_transactionQueries Begin TransactionAIdempotent
Begin an explicit transaction on the active session.
Inputs: no named parameters. Returns: object
queries_cancel_queryQueries Cancel QueryADestructive
Cancel an active running Snowflake query by its Query ID. Requires confirmation.
Inputs: query_id (required), confirm. Returns: object
queries_commit_transactionQueries Commit TransactionAIdempotent
Commit the current active transaction on the session.
Inputs: no named parameters. Returns: object
queries_execute_dmlQueries Execute DmlBDestructive
Execute a data modification SQL statement (INSERT, UPDATE, DELETE, MERGE, CREATE). Requires confirmation.
Inputs: statement (required), confirm. Returns: object
queries_get_query_historyQueries Get Query HistoryBRead-onlyIdempotent
Retrieve recent query execution history for the current account/user.
Inputs: limit. Returns: object
queries_get_query_operator_statsQueries Get Query Operator StatsBRead-onlyIdempotent
Retrieve operator-level execution statistics and profiling data for a past Query ID.
Inputs: query_id (required). Returns: object
queries_get_query_planQueries Get Query PlanARead-onlyIdempotent
Generate the EXPLAIN execution plan for a SQL query without executing it.
Inputs: query (required). Returns: object
queries_queryQueries QueryBRead-onlyIdempotent
Execute a SQL SELECT or read-only query on Snowflake and return structured rows with metadata.
Inputs: query (required), max_rows. Returns: object
queries_rollback_transactionQueries Rollback TransactionADestructive
Rollback the current active transaction on the session. Requires confirmation.
Inputs: confirm. Returns: object
recipes_account_usage_summaryRecipes Account Usage SummaryARead-onlyIdempotent
Composite recipe: Summary of warehouse compute credits and storage consumption over the past 7 days.
Inputs: no named parameters. Returns: object
recipes_clone_table_recipeRecipes Clone Table RecipeA
Composite recipe: Clone table with Time Travel timestamp or statement ID in 1 call.
Inputs: source_table (required), target_table (required), at_or_before. Returns: object
recipes_discover_schema_lineageRecipes Discover Schema LineageBRead-onlyIdempotent
Composite recipe: Discover all tables and views in a schema along with their column definitions.
Inputs: database, schema_name. Returns: object
recipes_export_query_to_stageRecipes Export Query To StageC
Composite recipe: Unload query results to a stage as Parquet or CSV files.
Inputs: query (required), stage_location (required), header, file_format. Returns: object
recipes_health_checkRecipes Health CheckARead-onlyIdempotent
Composite recipe: Run health check on connection, active session, warehouse state, and credit consumption.
Inputs: no named parameters. Returns: object
recipes_inspect_table_with_sampleRecipes Inspect Table With SampleBRead-onlyIdempotent
Composite recipe: Describe table schema, row count, column types, and preview sample rows in 1 call.
Inputs: table_name (required), database, sample_rows, schema_name. Returns: object
recipes_profile_tableRecipes Profile TableBRead-onlyIdempotent
Composite recipe: Profile table metadata, row count, and column inventory.
Inputs: table_name (required), database, schema_name. Returns: object
recipes_warehouse_scale_and_executeRecipes Warehouse Scale And ExecuteBDestructive
Composite recipe: Safely scale up a warehouse, run a heavy query, and optionally restore previous size. Requires confirmation.
Inputs: query (required), target_size (required), warehouse_name (required), confirm, +1 more. Returns: object
schemas_clone_schemaSchemas Clone SchemaB
Create a zero-copy clone of a schema.
Inputs: source_schema (required), target_schema (required), database. Returns: object
schemas_create_schemaSchemas Create SchemaC
Create a new schema inside a specified database.
Inputs: name (required), comment, database, if_not_exists. Returns: object
schemas_describe_schemaSchemas Describe SchemaARead-onlyIdempotent
Describe schema properties, owner, and retention settings.
Inputs: schema_name (required), database. Returns: object
schemas_drop_schemaSchemas Drop SchemaBDestructive
Drop a schema in Snowflake. Requires confirmation flag.
Inputs: name (required), confirm, database. Returns: object
schemas_list_schemasSchemas List SchemasBRead-onlyIdempotent
List all schemas within a specific database or the current active database. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database. Returns: object
schemas_undrop_schemaSchemas Undrop SchemaB
Restore a recently dropped schema using Time Travel.
Inputs: name (required), database. Returns: object
stages_create_stageStages Create StageC
Create an internal named stage in Snowflake.
Inputs: stage_name (required), comment, database, schema_name, +1 more. Returns: object
stages_describe_stageStages Describe StageBRead-onlyIdempotent
Describe stage location URL, storage integration, and file format properties.
Inputs: stage_name (required), database, schema_name. Returns: object
stages_drop_stageStages Drop StageADestructive
Drop a stage in Snowflake. Requires confirmation.
Inputs: stage_name (required), confirm, database, schema_name. Returns: object
stages_list_stage_filesStages List Stage FilesBRead-onlyIdempotent
List files inside a Snowflake stage location (e.g. '@MY_STAGE/path/').
Inputs: stage_location (required), pattern. Returns: object
stages_list_stagesStages List StagesBRead-onlyIdempotent
List internal and external stages available in the active database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
stages_remove_stage_fileStages Remove Stage FileBDestructive
Remove a file from a stage location. Requires confirmation.
Inputs: stage_file_path (required), confirm. Returns: object
streams_create_streamStreams Create StreamC
Create a CDC stream on a table or view.
Inputs: on_table (required), stream_name (required), database, append_only, +2 more. Returns: object
streams_describe_streamStreams Describe StreamARead-onlyIdempotent
Describe stream metadata, source table, and stale status.
Inputs: stream_name (required), database, schema_name. Returns: object
streams_drop_streamStreams Drop StreamBDestructive
Drop a stream. Requires confirmation.
Inputs: stream_name (required), confirm, database, schema_name. Returns: object
streams_list_streamsStreams List StreamsBRead-onlyIdempotent
List table/view streams in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
streams_read_stream_changesStreams Read Stream ChangesBRead-onlyIdempotent
Query unconsumed CDC changes recorded in a stream (default 10 rows).
Inputs: stream_name (required), limit. Returns: object
tables_clone_tableTables Clone TableB
Create a zero-copy clone of an existing table.
Inputs: source_table (required), target_table (required). Returns: object
tables_create_tableTables Create TableC
Create a table in Snowflake with specified column definitions SQL.
Inputs: table_name (required), columns_sql (required), database, schema_name, +1 more. Returns: object
tables_describe_tableTables Describe TableBRead-onlyIdempotent
Describe column definitions, data types, nullability, and primary keys for a table or view.
Inputs: table_name (required), database, schema_name. Returns: object
tables_drop_tableTables Drop TableBDestructive
Drop a table in Snowflake. Requires confirmation flag.
Inputs: table_name (required), confirm. Returns: object
tables_get_table_ddlTables Get Table DdlBRead-onlyIdempotent
Retrieve the exact CREATE OR REPLACE TABLE/VIEW DDL definition for an object.
Inputs: object_name (required), object_type. Returns: object
tables_list_tablesTables List TablesBRead-onlyIdempotent
List tables in a database schema with row counts and bytes. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
tables_list_viewsTables List ViewsBRead-onlyIdempotent
List views in a database schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
tables_sample_tableTables Sample TableCRead-onlyIdempotent
Preview sample rows from a table (default 10 rows).
Inputs: table_name (required), sample_size. Returns: object
tables_truncate_tableTables Truncate TableADestructive
Truncate all data rows from a table while preserving schema. Requires confirmation.
Inputs: table_name (required), confirm. Returns: object
tables_undrop_tableTables Undrop TableA
Restore a recently dropped table using Time Travel.
Inputs: table_name (required). Returns: object
tags_describe_tagTags Describe TagARead-onlyIdempotent
Describe tag properties, allowed values, and comment. A name in double quotes, such as a list row's quoted_name, must match exactly.
Inputs: tag_name (required), database, schema_name. Returns: object
tags_get_object_tag_referencesTags Get Object Tag ReferencesBRead-onlyIdempotent
Get tag key/value assignments on a specific database object.
Inputs: object_name (required), object_domain. Returns: object
tags_list_tagsTags List TagsBRead-onlyIdempotent
List object tags defined in a database or schema. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
tags_set_object_tagTags Set Object TagCIdempotent
Set or assign a tag value on a Snowflake object (TABLE, SCHEMA, DATABASE, etc.).
Inputs: tag_name (required), tag_value (required), object_name (required), object_domain. Returns: object
tasks_create_taskTasks Create TaskA
Create a task. schedule is optional and is omitted from CREATE TASK when unset. EXECUTE TASK runs a standalone or root task once; it does not run a child task. A child runs after its predecessors (AFTER), a finalizer runs with FINALIZE, and a triggered task uses WHEN (for example SYSTEM$STREAM_HAS_DATA) with no schedule. This tool sets only an optional SCHEDULE; it does not set AFTER, FINALIZE, or WHEN. Resuming fails unless the task has a SCHEDULE, AFTER, FINALIZE, or WHEN trigger.
Inputs: task_name (required), sql_statement (required), database, schedule, +3 more. Returns: object
tasks_describe_taskTasks Describe TaskARead-onlyIdempotent
Describe task definition, schedule, warehouse, and definition SQL.
Inputs: task_name (required), database, schema_name. Returns: object
tasks_drop_taskTasks Drop TaskADestructive
Drop a task in Snowflake. Requires confirmation.
Inputs: task_name (required), confirm, database, schema_name. Returns: object
tasks_execute_taskTasks Execute TaskBDestructive
Trigger an immediate one-time execution of a task. Requires confirmation.
Inputs: task_name (required), confirm, database, schema_name. Returns: object
tasks_list_tasksTasks List TasksBRead-onlyIdempotent
List tasks in a database or schema with schedule, state, and predecessor info. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern, database, schema_name. Returns: object
tasks_resume_taskTasks Resume TaskAIdempotent
Resume a suspended task. Snowflake error 091453 means the task has no SCHEDULE, AFTER, FINALIZE, or WHEN trigger. A schedule-less task can still be run once with EXECUTE TASK.
Inputs: task_name (required), database, schema_name. Returns: object
tasks_suspend_taskTasks Suspend TaskBIdempotent
Suspend an active scheduled task.
Inputs: task_name (required), database, schema_name. Returns: object
warehouses_create_warehouseWarehouses Create WarehouseC
Create a new virtual warehouse in Snowflake.
Inputs: warehouse_name (required), comment, auto_resume, auto_suspend, +2 more. Returns: object
warehouses_describe_warehouseWarehouses Describe WarehouseARead-onlyIdempotent
Describe details and running state of a specific virtual warehouse. A name in double quotes, such as a list row's quoted_name, must match exactly.
Inputs: warehouse_name (required). Returns: object
warehouses_drop_warehouseWarehouses Drop WarehouseBDestructive
Drop a virtual warehouse. Requires confirmation.
Inputs: warehouse_name (required), confirm. Returns: object
warehouses_get_warehouse_load_historyWarehouses Get Warehouse Load HistoryCRead-onlyIdempotent
Get execution load, queuing, and provisioning history for a warehouse.
Inputs: warehouse_name (required). Returns: object
warehouses_list_warehousesWarehouses List WarehousesBRead-onlyIdempotent
List virtual warehouses in the account with size, state, and auto-suspend configurations. Each row also has quoted_name, the name in double quotes, and, when the row has a database and schema, quoted_qualified_name.
Inputs: pattern. Returns: object
warehouses_resize_warehouseWarehouses Resize WarehouseB
Change warehouse compute size (XSMALL, SMALL, MEDIUM, LARGE, XLARGE, 2XLARGE, etc.).
Inputs: size (required), warehouse_name (required). Returns: object
warehouses_resume_warehouseWarehouses Resume WarehouseBIdempotent
Resume a suspended virtual warehouse.
Inputs: warehouse_name (required). Returns: object
warehouses_suspend_warehouseWarehouses Suspend WarehouseAIdempotent
Suspend an active virtual warehouse to save compute costs.
Inputs: warehouse_name (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 140 tools
Most tools are clearly scoped by resource and action, but the huge surface creates overlapping families such as tables/views/dynamic tables/Iceberg tables and list/describe variants. Composite recipes also duplicate underlying tools like describe/sample/clone, so an agent has multiple plausible choices for similar tasks.
Tool names broadly follow a predictable snake_case category_prefix + verb_noun pattern, e.g. tables_list_tables and warehouses_suspend_warehouse. Minor deviations exist, such as recipes_clone_table_recipe, occasional get_ vs describe_ usage, and domain-specific suffixes like embed_text_768.
With 140 tools, this is far beyond a well-scoped MCP surface and exceeds the extreme-mismatch threshold. The breadth mirrors much of Snowflake, but it imposes very high selection and context burden for an agent.
Core objects such as databases, schemas, tables, warehouses, stages, streams, tasks, pipes, roles, and users have useful lifecycle coverage. However, many resources are read-only or lack create/drop/alter operations, including grants, views, policies, procedures/functions/secrets, dynamic/Iceberg tables, and SPCS resources, leaving notable gaps despite generic SQL fallbacks.
Maintenance
Related MCP Connectors
Connect AI agents to 1000+ apps with managed authentication and tool-calling.
Connect your AI agent to 300+ methods and 100+ live tools
One place to build, share, and govern the skills and tools your AI agents use at work.
Connect AI agents to financial institution origination, analytics, and compliance workflows.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables intelligent data analysis and querying of Snowflake databases through specialized AI agents. Features 20+ tools for data operations, lineage tracing, usage analysis, and performance optimization with multi-agent architecture.-
- AlicenseAqualityNot gradedmaintenanceEnables AI assistants to securely connect to Snowflake data warehouses and execute SQL queries through natural language interactions. Supports multiple authentication methods and provides formatted query results with built-in security controls.12MIT
- AlicenseNot gradedqualityFmaintenanceEnables interaction with Snowflake through Cortex AI services including search, analyst, and agents for querying structured and unstructured data, plus SQL execution and object management capabilities.9,504 PyPI304Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform comprehensive Snowflake database operations including DDL, DML, and warehouse management. It allows users to query data, manage database objects, and configure permissions using natural language commands.MIT