MCP Clickhouse vs Snowflake Labs MCP

A side-by-side look at the MCP Clickhouse and Snowflake Labs MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

MCP Clickhouse logoMCP ClickhouseDatabases · Local subprocess (stdio)ClickHouse database integration with schema inspection and query capabilities67GreatAuth: otherSnowflake Labs MCP logoSnowflake Labs MCPDatabases · Local subprocess (stdio)Open-source MCP server for Snowflake from official Snowflake-Labs supports prompting Cortex Agents, querying structured & unstructured data, object management, SQL execution, semantic view querying, and more. RBAC, fine-grained CRUD controls, and all authentication methods supported.74GreatAuth: not declared

Verdict: choose MCP Clickhouse for databases work as a local process; choose Snowflake Labs MCP for databases as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

MCP Clickhouse logoChoose MCP Clickhouse when

  • You need dedicated capabilities in the Databases domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: other.
  • You want tools like list_databases, list_tables, run_query.
Explore MCP Clickhouse

Snowflake Labs MCP logoChoose Snowflake Labs MCP when

  • You need dedicated capabilities in the Databases domain.
  • You prefer a local stdio subprocess transport.
Explore Snowflake Labs MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecMCP Clickhouse logoMCP ClickhouseSnowflake Labs MCP logoSnowflake Labs MCP
CategoryDatabasesDatabases
Quality signal67/100 · Great74/100 · Great
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthotherNot declared
PricingFreeNot declared
Required env varsNone listedNone listed
Verified ownerCommunity listing Verified
GitHub stars892301
Directory activity 6 views 0 installs 0 upvotes 3 views 0 installs 0 upvotes
Tools3Not listed

Tools & capabilities

MCP Clickhouse tools 3

  • list_databasesList available ClickHouse databases
  • list_tablesList available ClickHouse tables in a database, including schema, comment, row count, and column count. Integers outside [-9007199254740991, 9007199254740991] in table metadata are returned as decimal strings. Pagination tokens are single-use and retained for up to one hour.
  • run_queryExecute SQL queries in ClickHouse. Queries run in read-only mode by default. Bind optional params by name with {name:Type} placeholders, such as {name:String} or {vector:Array(Float32)}. Values may be JSON scalars, nulls, or arrays. Pass exact large integers as decimal strings. JSON lists and objects cannot bind to Tuple and Map types. Python percent formatting and $name$ raw binary parameters are not supported. Parameter values stay out of the MCP server's normal SQL log lines, but may appear in errors and backend logs. Set CLICKHOUSE_ALLOW_WRITE_ACCESS=true to allow DDL and DML operations. Set CLICKHOUSE_ALLOW_DROP=true to additionally allow destructive operations (DROP, TRUNCATE, DELETE, UPDATE, REPLACE TABLE/PARTITION, CREATE OR REPLACE, CLEAR COLUMN/INDEX/PROJECTION, DETACH PERMANENTLY). That gate is a best-effort accident guard, not a security boundary. Integers outside [-9007199254740991, 9007199254740991] are returned as decimal strings. Two optional checks also run through this tool. Use DESCRIBE (<query>) when you need a query's output columns and types; it inspects the result schema and surfaces analysis errors such as an unknown column, but a query that describes cleanly can still fail at runtime. Consider EXPLAIN ESTIMATE <query> before a SELECT that could be expensive; it returns the estimated parts, rows and marks read from MergeTree family tables, which is not run time and not result size. Neither runs the query body, though analysis can execute scalar subqueries.

Snowflake Labs MCP tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

MCP Clickhouse

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "clickhouse-mcp-clickhouse": {
      "command": "uvx",
      "args": [
        "mcp-clickhouse"
      ]
    }
  }
}

Snowflake Labs MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "snowflake-labs-mcp": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp"
      ]
    }
  }
}

Frequently asked questions

MCP Clickhouse is categorized under Databases and uses a local stdio subprocess. Snowflake Labs MCP belongs to Databases and uses a local stdio subprocess. Pick MCP Clickhouse for databases work and Snowflake Labs MCP for databases.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

MCP Clickhouse is listed as free. Auth: other. Snowflake Labs MCP has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add clickhouse-mcp-clickhouse and snowflake-labs-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, MCP Clickhouse has a quality signal of 67/100 (Great) with 6 views, 0 installs and 892 GitHub stars. Snowflake Labs MCP has 74/100 (Great) with 3 views, 0 installs and 301 GitHub stars.