MaxCompute MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MaxCompute MCP Server list all tables in the MaxCompute project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MaxCompute MCP Server
Overview
A Model Context Protocol (MCP) server for MaxCompute.
Related MCP server: getdot-database-skills
Components
Tools
The server offers 4 core tools:
Query Tools
get_latest_partitionGet the latest partition name for a specific table
Input:
table_name(string): Name of the table
Returns: The latest partition name
read_queryExecute a SELECT query on the MaxCompute project, only SELECT query is allowed
Input:
query(string): The SELECT SQL query
Returns: Query results as array of objects
Schema Tools
list_tablesList all tables in the MaxCompute project
No input required
Returns: Array of table objects with name and comment
describe_tableGet the schema information for a specific table
Input:
table_name(string): Name of the table
Returns: Raw output of DESC command
Build from source
Code: GitHub
cd /path/to/maxcompute-mcp-server
uv pip install .
uv buildUsage with Cline
# Add the server to your cline_mcp_settings.json
"mcpServers": {
"maxcompute-mcp-server": {
"command": "uv",
"args": [
"run",
"--with",
"maxcompute-mcp-server",
"maxcompute-mcp-server"
],
"env": {
"ALIBABA_CLOUD_ACCESS_KEY_ID": "",
"ALIBABA_CLOUD_ACCESS_KEY_SECRET": "",
"ALIBABA_CLOUD_MAXCOMPUTE_PROJECT": "",
"ALIBABA_CLOUD_MAXCOMPUTE_ENDPOINT": "https://service.cn-shanghai.maxcompute.aliyun.com/api"
}
}
}Available Tools
4 toolsdescribe_tableA
Get the schema information for a specific table
Inputs: table_name (required).
get_latest_partitionC
Get the latest partition name for a specific table
Inputs: table_name (required).
list_tablesA
List all tables in the MaxCompute project
Inputs: no named parameters.
read_queryC
Execute a SELECT query on the MaxCompute project, only SELECT query is allowed
Inputs: query (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a distinct purpose: describing table schema, getting latest partition, listing tables, and executing SELECT queries. No overlap.
All tool names follow a consistent verb_noun pattern with underscores: describe_table, get_latest_partition, list_tables, read_query.
4 tools is reasonable for a focused MaxCompute server covering essential table inspection and querying operations, though some users might expect a few more utility tools.
Covers the main use cases for exploring and querying tables in MaxCompute (list, describe, get latest partition, query). Minor gaps like fetching specific partitions or writing data, but sufficient for typical read-only scenarios.
Maintenance
Related MCP Connectors
Text-to-SQL MCP server: read-only queries on PostgreSQL, MySQL and SQL Server with your real schema
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Official Microsoft MCP Server to query Microsoft Entra data using natural language
Related MCP Servers
- AlicenseCqualityDmaintenanceAn MCP server that enables natural language interaction with Apache Iceberg data lakehouses, allowing users to query table metadata, schemas, and properties through Claude, Cursor, or other MCP clients.541Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server providing a single query tool to execute SQL against GetDot Database, enabling schema discovery, data loading, and querying via natural language.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to query Spark SQL clusters via the Thrift/HiveServer2 protocol.21 PyPI1MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables Claude to query multiple databases (PostgreSQL, ClickHouse, MaxCompute) with automatic schema discovery and intelligent table search.-