Clickzetta MCP Server
@MCP-Mirror
About Clickzetta MCP Server
Mirror of
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"yunqiqiliang_mcp-clickzetta-server": {
"command": "uv",
"args": [
"pip",
"install",
"-e",
".",
"-i",
"https://pypi.tuna.tsinghua.edu.cn/simple/"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Clickzetta MCP Server?
A Model Context Protocol (MCP) server that provides database interaction with Clickzetta Lakehouse, enabling SQL query execution and management of a data insights memo. It is built for developers and analysts who need to query and analyze data in Clickzetta through AI assistants like Claude Desktop.
How to use Clickzetta MCP Server?
Install locally by cloning the repository and running uv pip install -e ., then configure credentials in a .env file. Start the stdio-based server with uv run mcp_clickzetta_server and integrate it into Claude Desktop's MCP Servers settings using the uv executable path. Optionally install via Smithery (npx -y @smithery/cli@latest install @yunqiqiliang/mcp-clickzetta-server) or UVX (uvx mcp_clickzetta_server with command-line arguments).
Key features of Clickzetta MCP Server
- Execute SELECT queries to read database data
- Perform INSERT, UPDATE, DELETE with
--allow-writeflag - Create new tables via
create_tabletool - List all tables and describe table schemas
- Append data insights to a continuously updated memo resource
- Read-only operations enforced by default with auto-added LIMIT clauses
Use cases of Clickzetta MCP Server
- Querying Clickzetta Lakehouse data through natural language via Claude Desktop
- Exploring table schemas and relationships across schemas
- Building analysis reports and dashboards from query results
- Documenting data insights in a persistent memo that updates automatically
FAQ from Clickzetta MCP Server
What tools does Clickzetta MCP Server provide?
Six core tools: read_query for SELECT queries, write_query for modifications (with --allow-write), create_table (with --allow-write), list_tables, describe-table for schema inspection, and append_insight for adding insights to the memo.
What are the security precautions?
Write operations (INSERT, UPDATE, DELETE, CREATE TABLE) require explicit --allow-write flag. The server automatically adds LIMIT clauses to prevent large result sets and uses service account authentication. Input validation guards against SQL injection.
What credentials are required?
A .env file must contain Clickzetta username, password, service URL, instance, workspace, schema, and vcluster. Keep this file secure and never commit it to version control.
How does the memo resource work?
The memo://insights resource aggregates data insights discovered during analysis. Insights are added via the append_insight tool, and the memo auto-updates as new insights are appended.
How can I exclude tools?
Use the --exclude_tools flag followed by tool name(s) when starting the server via UVX. Multiple tools can be excluded by repeating the argument.
More Other MCP servers
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
ICSS
chokcoco不止于 CSS
Comments