Agent Skills › Canner/wren-engine › wren-connection-info

wren-connection-info

GitHub

提供Wren Engine连接18种数据源（数据库、云存储）的配置参考，涵盖字段要求、Docker网络提示及敏感信息处理，指导用户通过Web UI正确配置连接。

skills-archive/wren-connection-info/SKILL.md Canner/wren-engine

Trigger Scenarios

询问如何配置数据源连接查询特定数据源的必填字段

Install

npx skills add Canner/wren-engine --skill wren-connection-info -g -y

More Options

Non-standard path

npx skills add https://github.com/Canner/wren-engine/tree/main/skills-archive/wren-connection-info -g -y

Use without installing

npx skills use Canner/wren-engine@wren-connection-info

指定 Agent (Claude Code)

npx skills add Canner/wren-engine --skill wren-connection-info -a claude-code -g -y

安装 repo 全部 skill

npx skills add Canner/wren-engine --all -g -y

预览 repo 内 skill

npx skills add Canner/wren-engine --list

SKILL.md

Frontmatter

{
    "name": "wren-connection-info",
    "license": "Apache-2.0",
    "metadata": {
        "author": "wren-engine",
        "version": "1.5"
    },
    "description": "Reference guide for Wren Engine connection info — explains required fields for all 18 supported data sources (PostgreSQL, MySQL, BigQuery, Snowflake, ClickHouse, Trino, DuckDB, Databricks, Spark, Athena, Redshift, Oracle, SQL Server, Apache Doris, S3, GCS, MinIO, local files). Covers sensitive field handling, Docker host hints, and BigQuery credential encoding. Use when the user asks how to configure a data source connection or what fields to fill in."
}

Wren Connection Info Reference

Connection info can only be configured through the MCP server Web UI at http://localhost:9001. Do not attempt to set it programmatically. Always direct the user to the Web UI.

Supported data sources

Value	Database	Fields reference
`POSTGRES`	PostgreSQL	databases.md
`MYSQL`	MySQL / MariaDB	databases.md
`MSSQL`	SQL Server	databases.md
`CLICKHOUSE`	ClickHouse	databases.md
`ORACLE`	Oracle	databases.md
`DORIS`	Apache Doris	databases.md
`REDSHIFT`	Amazon Redshift	databases.md
`TRINO`	Trino	databases.md
`BIGQUERY`	Google BigQuery	databases.md
`SNOWFLAKE`	Snowflake	databases.md
`DUCKDB`	DuckDB	databases.md
`ATHENA`	AWS Athena	databases.md
`DATABRICKS`	Databricks	databases.md
`SPARK`	Apache Spark	databases.md
`S3_FILE`	Amazon S3	file-sources.md
`GCS_FILE`	Google Cloud Storage	file-sources.md
`MINIO_FILE`	MinIO	file-sources.md
`LOCAL_FILE`	Local files	file-sources.md

Read the linked reference file for the user's data source to get required fields, default ports, and setup notes.

Common patterns

Most database connectors need: host, port, user, password, database.

Exceptions:

BigQuery — uses project_id, dataset_id, credentials (base64-encoded). See databases.md for encoding instructions.
Snowflake — uses account instead of host, plus schema.
Trino — needs catalog and schema instead of database.
Databricks — uses serverHostname, httpPath, accessToken (or service principal with clientId, clientSecret).
Spark — only host and port (Spark Connect protocol, no auth fields).
File sources — use url, format, plus bucket/credentials. See file-sources.md.

Docker host hint

If the database runs on the host machine and Wren Engine runs inside Docker, localhost cannot reach the host. Use host.docker.internal instead:

Original	Inside Docker
`localhost`	`host.docker.internal`
`127.0.0.1`	`host.docker.internal`
Cloud/remote hostname	No change needed

Sensitive fields

Never log, display, or pass sensitive values through the AI agent unnecessarily.

Connector	Sensitive fields
Postgres / MySQL / MSSQL / ClickHouse / Oracle / Doris / Redshift	`password`
BigQuery	`credentials`
Snowflake	`password`
Athena	`aws_access_key_id`, `aws_secret_access_key`
Databricks (token)	`accessToken`
Databricks (service principal)	`clientId`, `clientSecret`
S3 / MinIO	`access_key`, `secret_key`
GCS	`key_id`, `secret_key`, `credentials`
Trino / Spark / Local files	(none)