Skip to main content
Glama
726,822 tools. Updated 2026-10-30 23:38

"snowflake" matching MCP tools:

Matching MCP Servers

  • snowflake

    eranrh86
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables read-only Snowflake database queries through MCP, allowing safe SELECT, SHOW, DESCRIBE, WITH, and EXPLAIN operations via natural language tools with lazy connection setup.
    MIT

  • snowflake-mcp

    faressoft
    A
    license
    A
    quality
    D
    maintenance
    Enables AI agents to execute SQL queries and explore Snowflake databases using natural language, with schema discovery, table inspection, and readonly mode.
    11
    446 npm
    MIT

Matching MCP Connectors

  • sdk_guideA

    SenzingA

    Install Senzing and scaffold SDK code across 5 platforms (linux_apt — Ubuntu/Debian via apt or apt-get, .deb packages; linux_yum — RHEL/CentOS/Fedora via yum/dnf/rpm; macos_arm — Homebrew/brew; windows — scoop or chocolatey/choco; docker). Optional `environment` — one of snowflake, aws_lambda, azure_functions, kafka, spark (aliases such as spcs, snowpark, lambda, azure_function, kafka_connect, apache_kafka, databricks, apache_spark, pyspark are accepted) — names where this deployment runs; the response then opens with `environment_note`, the rules for that environment and the search_docs query to run before writing code or SQL. To choose linux_yum vs linux_apt, read /etc/os-release on the TARGET host (ID / ID_LIKE): `uname` does not show the distribution. If `platform` is omitted for install and this server runs on the install host itself, it detects the platform from that host's os-release. Languages: 5 (Python, Java, C#, Rust, TypeScript). Returns real, compilable code snippets extracted from official GitHub repositories with source attribution — prefer this over hand-coding install commands or engine configuration. When this server carries the SDK packages for the chosen platform (.deb for linux_apt, .rpm for linux_yum, the macOS packages for macos_arm, and the .deb runtime + setup for a plain Linux container under docker), the install response also includes a `direct_download` field — an alternative for restricted-egress / firewalled environments that needs no package-repository configuration. Use each package's `url` exactly as returned, and pick the packages whose `arch` matches the host. Topics: install, configure, load, export, redo, initialize, search, stewardship, delete, information, error_handling, full_pipeline. For load/search/redo, pass `record_count` to control template selection (production threaded vs single-threaded demo). Export redirects to reporting_guide. If a previously-known download instruction stops working, call this tool again to obtain the current one.
    ConnectorNo auth

  • create_diagramA

    mcpA

    When: use when Datadef's own model should design a whole new diagram from a description or a pasted schema. To build it yourself step by step, use create_blank_diagram; to change an existing diagram, canvas_view and the canvas_* tools, or edit_diagram. Generates a professional data architecture diagram from a description and saves it to the user's Datadef account. Use it for any data-shaped diagram: medallion and lakehouse architectures, ETL/ELT pipelines, streaming topologies, data mesh, star and snowflake schemas, ER diagrams, lineage maps, cloud architectures, and data platform designs. EXISTING SCHEMAS: if the conversation or the repository has the schema itself (SQL DDL, a MySQL or pg_dump export, migrations, schema.prisma), pass the file contents as the prompt, unedited. Datadef parses it instead of asking a model: every table, column, type, primary key and foreign key comes out exactly as written, in seconds. Warehouse DDL with no declared foreign keys (fact_sales.customer_key → dim_customer.customer_key) gets its links from key names, drawn dashed. Add a sentence only if you want something other than a picture of that schema; "turn these tables into a star schema" or "design the pipeline that loads them" goes to the model instead. Write a specific prompt. Name the actual technologies (Snowflake, dbt, Airflow, Kafka, Fivetran), the layers or zones you want, and the tables that matter, the diagram is only as detailed as the description. Zone names you give are treated as a specification, not a suggestion. SCOPE: if the user's request is open-ended ("diagram our platform", "show me something"), ask them how much detail they want before calling this, or say which scope you chose. Default to scope "overview". A dense 40-node diagram is impressive and usually not what someone wanted from a one-line request; they can always ask you to expand it. TIMING: this waits up to ~35 seconds; fast generations come back finished, with a preview image and a markdown line to show the user. Slower ones (1-3 minutes total) return a diagram_id while generation continues: call get_diagram with that id after ~60 seconds (poll every 30s) to get the finished diagram. If you cannot call tools again on your own, never leave the user empty-handed: give them the Open link, say it will be ready in about a minute, and offer to show the diagram inline when they next ask. Never call create_diagram a second time while one is still generating; you would create a duplicate. Do not use image generation for these. This produces a real, editable diagram. Next: show the user the preview line it returns; to adjust the result, canvas_view then the targeted canvas_* tools.
    ConnectorAPI key

  • list_referencesA

    Cloud FinOps Skill & MCPA

    See what FinOps guidance is available: billing mechanics, commitment strategy, allocation and chargeback, AI cost management, and per-provider cost handbooks (AWS, Azure, GCP, OCI, Databricks, Snowflake, ...). Use this to discover what the library covers before deciding what to fetch. When the question already names a FinOps domain, phase, persona or maturity, call ``find_references`` instead of scanning this full list. Returns a dict shaped ``{"references": [...], "total": N}`` where each entry includes ``name``, ``title``, a one-line ``description``, the discriminating FCP facets (``fcp_domain``, ``fcp_capability``, ``fcp_phases``, ``fcp_personas_primary``, ``fcp_maturity_entry``) and ``approx_tokens``. Read ``approx_tokens`` before fetching: the library runs from about 2,000 to about 15,000 tokens per file. Above roughly 10,000, prefer ``get_reference(name, section=...)`` and pull the part you need.
    ConnectorNo auth

  • fastero_set_dashboard_refreshA

    FasteroA

    Set how a dashboard refreshes its charts for everyone who has it open: minutes (1, 5, 15 or 60; 0 turns it off), or when: 'change' to refresh when the data behind its charts changes. A hosted page's refresh is set with fastero_set_page_refresh instead, and fastero_disable_trigger pauses this one by its triggerId while keeping it. 'change' needs a chart whose query runs on Postgres or BigQuery, and a chart on a warehouse that bills each query (BigQuery, Snowflake, Athena, S3) makes 5 minutes the shortest timer; a value it cannot use is refused with the reason. Only open screens re-run their charts, and its public link re-takes its numbers when someone opens it; a scheduled email (fastero_schedule_dashboard_email) runs its own queries whatever is set here. Returns refresh, the setting now in force ({ triggerId, mode: timer or change, minutes }, or null when off), as fastero_get_dashboard reports it. Owners, admins and editors of the project can set it.
    ConnectorAPI key

  • fastero_set_page_refreshA

    FasteroA

    Set how a hosted page refreshes its numbers for everyone who has it open: minutes (1, 5, 15 or 60; 0 turns it off), or when: 'change' to refresh when the data behind its widgets changes. A dashboard's refresh is set with fastero_set_dashboard_refresh instead, and fastero_disable_trigger pauses this one by its triggerId while keeping it. 'change' needs a widget whose query runs on Postgres or BigQuery, and a page that has one gets it from the start; a widget on a warehouse that bills each query (BigQuery, Snowflake, Athena, S3) makes 5 minutes the shortest timer. A value it cannot use is refused with the reason. Only open screens re-read their rows. Returns refresh, the setting now in force ({ triggerId, mode: timer or change, minutes }, or null when off). Owners, admins and editors of the project can set it.
    ConnectorAPI key

  • import_snowflake_lineageA

    WavelengthA

    Map data lineage in one Snowflake database into a new Wavelength flow, with no AI call. Read-only queries on ACCOUNT_USAGE: object dependencies (views on tables), access history writes (INSERT ... SELECT, CTAS, MERGE; Enterprise edition), and stage or Snowpipe loads. Tables and stages become data nodes, views and dynamic tables become steps, edges are labeled references, writes, COPY INTO, or the Snowpipe name. Pass schema to keep only that schema and its direct neighbors (limit 250 nodes). Returns the flow link and which lineage sources returned rows.
    ConnectorOAuth

  • fastero_create_connectionA

    FasteroA

    Create a data connection to a database that signs in with a username and password (Postgres, MySQL, SQL Server, Redshift, Snowflake, Oracle), available to the whole organisation. The credentials given in creds, the password among them, pass through the model and are kept in plain text in the client session transcript, so creating a direct-credential connection in the Fastero web app is the preferred route. OAuth sources such as BigQuery and Google Sheets cannot be created this way and need a browser sign-in; an uploaded CSV or Excel file becomes a connection with fastero_create_file_connection. It connects before saving, so a database it cannot reach is not saved. The refusal names a common cause, such as a wrong password, an unknown host or Oracle service, or a firewall that needs Fastero's address allowed; any other gives the driver's error code and the settings to check. For a Postgres, MySQL, SQL Server, Redshift or Oracle database behind an SSH bastion, creds also takes sshHost, sshPort (22), sshUsername, sshKeyId from fastero_create_ssh_key, and sshHostKey; host is then the database's host as the bastion reaches it, and for Oracle its IP address. A first call without sshHostKey is refused with the bastion's host-key fingerprint, which the person can compare on the bastion; the same call with it as sshHostKey goes ahead. Returns the new connection's _id, the connectionId other tools take. Owners, admins and editors of the organisation can create one.
    ConnectorAPI key

  • transpile_sqlA

    AI NetCaféA

    Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.
    ConnectorNo auth

  • transpile_sqlA

    netcafe-live-dataA

    Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.
    ConnectorNo auth

  • transpile_sqlA

    netcafe-devkitA

    Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.
    ConnectorNo auth

  • transpile_sqlA

    ai-netcafeA

    Convert a SQL statement from one dialect to another — mysql, postgres, sqlite, tsql, oracle, snowflake, bigquery, redshift, spark, hive, presto, trino, duckdb, clickhouse, databricks, doris, starrocks and more. Deterministic parser (sqlglot), not an LLM: the same input always produces the same output, and syntax errors come back with the exact line and column. Use it when migrating queries between databases or debugging dialect-specific syntax.
    ConnectorNo auth

  • canvas_search_iconsA

    mcpA

    When: Use before adding nodes that should show a vendor logo (Snowflake, Kafka, Power BI) and you are unsure of the icon id. Find icon ids in Datadef's library (2000+ cloud and data-tool logos) by product name, e.g. "Amazon Aurora PostgreSQL", "k8s", "Azure Event Hubs". Pass `queries` to look up many names in one call (best id per name); pass `query` for the top matches of one name. Scores: 90+ sure, 75+ good. A name with no match has no icon; leave the icon field out rather than guessing. Batch: Pass `queries` with every vendor at once (up to 40, best id per name) instead of one call per vendor. Next: canvas_add_nodes (or canvas_update_nodes) with icon set to a returned id; omit icon when nothing matched.
    ConnectorAPI key

  • canvas_replace_nodeA

    mcpA

    When: Use when one component changes identity or type (Redshift becomes Snowflake, a card becomes a service icon). The node keeps its id, connections, lineage, zone, position and fields. Turn a node into a different component in place — Redshift becomes Snowflake, a batch job becomes streaming. It keeps its id, every connection and lineage row, its zone, position, owners, schedule, colours and columns; only what you pass changes (a new label with no icon picks the new product's icon). canvas_update_nodes does the same for many nodes at once. Batch: One node per call. To convert many nodes, use canvas_update_nodes with `type` (and `label`, `icon`) for each, in one call. Operates on one Datadef diagram, named by diagram_id. Returns compact JSON: the ids it created, changed or removed, the diagram revision, a one-line summary and the next step. A viewer-role account is refused. Next: canvas_view to check the result.
    Connector
    Destructive
    API key

  • fastero_list_connectionsA

    FasteroA

    List every data connection in this organisation, from all its projects, to pick the connectionId that fastero_run_sql, fastero_list_connection_schemas, fastero_create_query and fastero_show_chart take. Each comes with its _id, name, datasource (pg for Postgres, mysql2, mssql, snowflake, bq for BigQuery, duckdb for an uploaded file, and others), database (the database's name; for BigQuery, the project id), who created it and when. No credentials, hosts or test results: fastero_get_connection reads one connection's settings and last test, and fastero_list_connection_schemas its tables. Any member of the organisation can list them. orgId can be left out: it can only be the organisation this key belongs to.
    ConnectorAPI key

  • fastero_run_sqlA

    FasteroA

    Run a read-only query against one of this organisation's connected databases — PostgreSQL, MySQL, SQL Server, Redshift, Snowflake, Oracle, BigQuery or Google Sheets, or an uploaded CSV or Excel file made queryable with fastero_create_file_connection (DuckDB) — in that connection's own SQL dialect, and return rows. One SELECT, WITH, EXPLAIN or SHOW statement; a statement that could change data is refused. It returns at most 500 rows and about 100 KB: a larger result comes back cut, with truncated: true and totalRows, so prefer a LIMIT or an aggregate. Where a question involves a business number (revenue, churn, active users…), fastero_get_definitions holds this organisation's own expression for it.
    ConnectorAPI key