Connector guide1-minute read8 MCP toolsEN · DE · IT

如何将 Postgres 连接到 Gemini — 通过 MCP

Direct Postgres connection over libpq — execute SELECT/EXPLAIN queries, list schemas/tables/indexes, sample rows, fetch column stats. Read-only role recommended for AI use.

HCBy HelpCode teamUpdated 1 min read Open source on GitHub

No credit card · 7-day trial · Self-host alternative available

Postgres

MCP connector

Postgres

Direct Postgres connection over libpq — execute SELECT/EXPLAIN queries, list schemas/tables/indexes, sample rows, fetch column stats. Read-only role recommended for AI use.

Tools

8

Region

SELF-HOST

Category

Data & Analytics

Authentication

Basic Auth

Required env vars

POSTGRES_URL
Install in one click on Cloud

7-day free trial · No credit card

  • 7-day free trial
    No credit card required
  • GDPR & SOC 2 ready
    EU data residency, audit logs
  • Open-source on GitHub
    Source-available BSL-1.1
  • Works with ChatGPT, Claude, Gemini
    Any MCP-compatible client

Skip the install. Get this working in under 2 minutes.

Start a free trial on cloud.anythingmcp.com, add the Postgres in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.

Start free trial

Summary

Direct Postgres connection over libpq — execute SELECT/EXPLAIN queries, list schemas/tables/indexes, sample rows, fetch column stats. Read-only role recommended for AI use.

试试这样问

Postgres 的示例提示

点击任意提示即可复制,然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中,在该连接器上运行。

Postgres · 通过 MCP 实时
分享
Opus 4.7

Claude 是 AI,可能会出错。请核对回答。

💡 无需安装? 直接使用 cloud.anythingmcp.com 登录、点击 Connectors → Postgres、粘贴凭证、生成 MCP API key — 完成。无 Docker、无 git clone、无本地服务器。

Postgres + Gemini

Direct Postgres connection over libpq — execute SELECT/EXPLAIN queries, list schemas/tables/indexes, sample rows, fetch column stats. Read-only role recommended for AI use.

前提条件

完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:

POSTGRES_URL

步骤 1 — 获取凭证

步骤 2 — 安装 adapter

git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d

步骤 3 — 在 Gemini 中添加连接器

Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
    }
  }
}
  1. 从 AnythingMCP 获取你的 MCP API key
  2. 保存文件并重启 gemini
  3. 在 Gemini CLI 中运行 /mcpPostgres 应显示为可用。
  4. Vertex AI Studio: 将 https://cloud.anythingmcp.com/mcp 传入请求的 tools 数组,使用相同的 Bearer 头。

可用工具

FAQ

Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。

下一步

这份指南对你有帮助吗?

Ready to ship

Your Postgres agent is one click away.

Install the connector, paste the key, prompt Gemini. Free for 7 days, no credit card.

相关指南