MCP.so
ログイン

Hologres MCP Server

@aliyun

Hologres MCP Server について

概要はまだありません

基本情報

カテゴリ

その他

ライセンス

Apache-2.0

ランタイム

python

トランスポート

stdio

公開者

aliyun

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "alibabacloud-hologres-mcp-server": {
      "command": "uvx",
      "args": [
        "hologres-mcp-server",
        "--transport",
        "streamable-http",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ]
    }
  }
}

ツール

39

Execute a SELECT SQL query in Hologres database

Execute a SELECT SQL query in Hologres database with serverless computing

Execute a DML (INSERT, UPDATE, DELETE) SQL query in Hologres database

Execute a DDL (CREATE, ALTER, DROP, COMMENT ON) SQL query in Hologres database

Collect table statistics in Hologres database

Get query plan in Hologres database

Get execution plan in Hologres database

Invoke a procedure in Hologres database

Create MaxCompute foreign tables in Hologres database.

Lists all schemas in the current Hologres database, excluding system schemas.

Lists all tables in a specific schema, including their types (table, view, external table, partitioned table).

Show the DDL script of a table, view, or external table in the Hologres database.

Execute a SELECT SQL query and generate a chart (bar, line, scatter, pie, histogram, area). Returns query results and a base64-encoded PNG image.

Analyze a specific query's performance profile by its query_id from hg_query_log. Returns detailed metrics including duration, memory, CPU time, read/write stats.

Get slow queries from hg_query_log ordered by duration.

List all Dynamic Tables with their status, freshness settings, and last refresh info.

Get refresh history for a specific Dynamic Table, including duration, status, and latency.

List all tables in the Hologres recycle bin (dropped tables that can be restored).

Restore a dropped table from the Hologres recycle bin.

List all computing groups (warehouses) with their CPU, memory, cluster count, and status.

Switch the current session's computing resource to a specified warehouse.

Get storage size details of a table, including total, data, index, and metadata breakdown.

Cancel or terminate a running query by its process ID.

List currently active queries and connections from pg_stat_activity.

List all Query Queues and their classifiers (concurrency limits, routing rules). Requires V3.0+.

Get table properties including distribution_key, clustering_key, segment_key, bitmap_columns, binlog settings, etc.

Get table's Table Group and shard count info for diagnosing data skew.

List all External Databases and Foreign Servers for Lakehouse acceleration. Requires V3.0+.

Diagnose lock contention by showing blocking and waiting queries.

Get table storage trend from hg_table_info, showing daily storage size, file count, and row count changes.

Create, drop, or clear a Query Queue. Requires V3.0+ and superuser privileges.

Create or drop a classifier for a Query Queue. Requires V3.0+.

Set or remove properties on a Query Queue or classifier. Requires V3.0+.

Manage a computing group: suspend, resume, restart, rename, or resize. Requires superuser.

Get detailed running status and scaling progress of a computing group.

Trigger shard rebalancing for a computing group to eliminate data skew.

List all data masking rules configured via hg_anon extension (column-level and user-level).

Query files directly from OSS using EXTERNAL_FILES function without creating foreign tables. Requires V4.1+.

Get the current value of a GUC (Grand Unified Configuration) parameter.

概要

What is Hologres MCP Server?

Hologres MCP Server serves as a universal interface between AI Agents and Hologres databases. It enables seamless communication between AI Agents and Hologres, helping AI Agents retrieve Hologres database metadata and execute SQL operations.

How to use Hologres MCP Server?

Configure via an MCP client configuration file (e.g., using uv, uvx, or pip). Set environment variables (HOLOGRES_HOST, HOLOGRES_PORT, HOLOGRES_USER, HOLOGRES_PASSWORD, HOLOGRES_DATABASE) and specify the command and arguments. Alternatively, use Streamable HTTP transport for remote deployment: start with hologres-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000. Use with Claude Code via claude mcp add hologres-mcp-server.

Key features of Hologres MCP Server

  • Execute SELECT, DML, and DDL SQL queries on Hologres
  • Retrieve metadata: schemas, tables, views, external tables, DDL
  • Collect table statistics and get query plans
  • Analyze slow queries and active queries
  • Manage dynamic tables, query queues, warehouses, and recycling bin
  • Generate charts from query results (bar, line, scatter, pie, histogram, area)
  • Access system information via resource templates

Use cases of Hologres MCP Server

  • AI‑powered database exploration and schema discovery
  • Automated SQL optimization and performance analysis
  • Monitoring and troubleshooting query performance
  • Managing Hologres resources (warehouses, query queues, dynamic tables)
  • Integration with AI coding assistants for data‑driven development

FAQ from Hologres MCP Server

What transport protocols does Hologres MCP Server support?

It supports stdio, streamable-http, and sse.

What environment variables are required?

HOLOGRES_HOST, HOLOGRES_PORT, HOLOGRES_USER, HOLOGRES_PASSWORD, and HOLOGRES_DATABASE.

How do I install Hologres MCP Server?

You can install via pip install hologres-mcp-server or clone from GitHub.

Can I run Hologres MCP Server remotely?

Yes, use --transport streamable-http to start an HTTP endpoint, then configure the client with a url.

Does Hologres MCP Server support Claude Code?

Yes, use claude mcp add hologres-mcp-server with the required environment variables and -- uvx hologres-mcp-server.

コメント

「その他」の他のコンテンツ