原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Secure Schema MCP

作者:Siddharth-coder13版本 1.0.1i★ –i在你的电脑上运行
注册名称io.github.Siddharth-coder13/secure-schema

安装

概览

作者提供的说明(英文原文)

Read-only MCP server for exposing database schema metadata without row data.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 数据库与数据集
  • 你需要填写:DATABASE_URL

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 需要你自己填写: DATABASE_URL, DATABASE_SCHEMA, ALLOWED_TABLES, SECURE_SCHEMA_ENV, FASTMCP_CHECK_FOR_UPDATES, FASTMCP_SHOW_SERVER_BANNER

标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。

你需要

  • PyPI已安装 Python 的 uv(用于 uvx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "secure-schema": {
      "command": "uvx",
      "args": [
        "mcp-secure-schema"
      ],
      "env": {
        "DATABASE_URL": "your-value",
        "DATABASE_SCHEMA": "your-value",
        "ALLOWED_TABLES": "your-value",
        "SECURE_SCHEMA_ENV": "your-value",
        "FASTMCP_CHECK_FOR_UPDATES": "your-value",
        "FASTMCP_SHOW_SERVER_BANNER": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add secure-schema --env DATABASE_URL=your-value --env DATABASE_SCHEMA=your-value --env ALLOWED_TABLES=your-value --env SECURE_SCHEMA_ENV=your-value --env FASTMCP_CHECK_FOR_UPDATES=your-value --env FASTMCP_SHOW_SERVER_BANNER=your-value -- uvx mcp-secure-schema

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "secure-schema": {
      "command": "uvx",
      "args": [
        "mcp-secure-schema"
      ],
      "env": {
        "DATABASE_URL": "your-value",
        "DATABASE_SCHEMA": "your-value",
        "ALLOWED_TABLES": "your-value",
        "SECURE_SCHEMA_ENV": "your-value",
        "FASTMCP_CHECK_FOR_UPDATES": "your-value",
        "FASTMCP_SHOW_SERVER_BANNER": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "secure-schema": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-secure-schema"
      ],
      "env": {
        "DATABASE_URL": "your-value",
        "DATABASE_SCHEMA": "your-value",
        "ALLOWED_TABLES": "your-value",
        "SECURE_SCHEMA_ENV": "your-value",
        "FASTMCP_CHECK_FOR_UPDATES": "your-value",
        "FASTMCP_SHOW_SERVER_BANNER": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • DATABASE_URL 机密 必填 env
    SQLAlchemy database URL used for schema inspection.
  • DATABASE_SCHEMA env
    Optional default schema or catalog namespace. In production it is locked and tool arguments cannot override it.
  • ALLOWED_TABLES env
    Optional comma-separated table/view allowlist. When set, only listed tables and views are visible.
  • SECURE_SCHEMA_ENV env
    Set to production to require ALLOWED_TABLES during startup.
  • FASTMCP_CHECK_FOR_UPDATES env
    Set to off to disable FastMCP startup update checks.
  • FASTMCP_SHOW_SERVER_BANNER env
    Set to false to suppress the FastMCP startup banner.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 Siddharth-coder13 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“数据库与数据集”中的其他服务器比较i

  • 星标数多于此分类中其他 953 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 953 个服务器的 18% 更新
  • 基础检查结果等于或优于此分类中其他 953 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Secure Schema MCP 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:DATABASE_URL

它在我的电脑上运行还是在云端?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(1.0.1)于4个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。

有什么可以替代它?

同一分类中有:Supabase, MongoDB MCP Server, Elasticsearch MCP Server

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Supabase

作者:supabase

MCP server for interacting with the Supabase platform

电脑或云端★ 2,993Apache-2.0昨天更新
安装

MongoDB MCP Server

作者:mongodb-js

MongoDB Model Context Protocol Server

在你的电脑上运行★ 1,157Apache-2.0前天更新
安装

MCP server for interacting with Elasticsearch

在你的电脑上运行★ 315Apache-2.014个月前更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Secure Schema MCP

A read-only MCP server that gives AI coding tools database structure without exposing row data. It returns table and view names, columns, types, keys, and relationships in a compact format designed to reduce LLM token usage.

What it exposes

ExposedNot exposed
Table and view namesRow values or query results
Column names and SQL typesRow counts or samples
Primary and unique keysDatabase credentials
Foreign-key relationshipsWrite or query tools

Schema metadata can still be sensitive. A column name such as ssn reveals information even without values, so production deployments should always use the table allowlist and a dedicated database account.

Requirements

  • An MCP-compatible client such as Cursor or Codex
  • A reachable SQLite, PostgreSQL, or MySQL database
  • Python 3.12 or newer when installing without uvx

SQLite support uses Python's built-in driver. PostgreSQL and MySQL drivers are included. Other SQLAlchemy dialects are not tested or bundled in v1.

Configure your IDE

The recommended setup uses uvx to download and run the published Python package in an isolated environment. You do not need to clone this repository or start the server separately. Your IDE launches it over stdio when needed.

Cursor

Add this server to your Cursor MCP configuration:

{

"mcpServers": { "secure-schema": { "command": "uvx", "args": ["mcp-secure-schema"], "env": { "DATABASE_URL": "postgresql+psycopg2://schema_reader:password@localhost:5432/appdb", "DATABASE_SCHEMA": "public", "ALLOWED_TABLES": "users,orders,products", "SECURE_SCHEMA_ENV": "production", "FASTMCP_CHECK_FOR_UPDATES": "off", "FASTMCP_SHOW_SERVER_BANNER": "false" } } } }

Restart or reload Cursor after changing its MCP configuration.

Codex

Add this to ~/.codex/config.toml or a trusted project's .codex/config.toml:

[mcp_servers.secure-schema]

command = "uvx" args = ["mcp-secure-schema"] enabled_tools = ["schema_overview", "list_tables", "inspect_table"] startup_timeout_sec = 30 tool_timeout_sec = 30

[mcp_servers.secure-schema.env] DATABASE_URL = "postgresql+psycopg2://schema_reader:password@localhost:5432/appdb" DATABASE_SCHEMA = "public" ALLOWED_TABLES = "users,orders,products" SECURE_SCHEMA_ENV = "production" FASTMCP_CHECK_FOR_UPDATES = "off" FASTMCP_SHOW_SERVER_BANNER = "false"

Install once instead

If you prefer a persistent installation:

pipx install mcp-secure-schema

Then use "command": "mcp-secure-schema" with an empty args list in the IDE configuration.

Database URLs

Secure Schema MCP accepts SQLAlchemy connection URLs:

# SQLite (absolute path)

sqlite:////Users/me/project/app.db

PostgreSQL

postgresql+psycopg2://user:password@localhost:5432/appdb

Remote PostgreSQL with certificate verification

postgresql+psycopg2://user:password@db.example.com:5432/appdb?sslmode=verify-full&sslrootcert=/path/to/ca.pem

MySQL

mysql+pymysql://user:password@localhost:3306/appdb

Percent-encode special characters in URL usernames and passwords. For example, @ in a password becomes %40.

Local and remote databases use the same MCP configuration. For remote databases, the machine running the IDE must also have working DNS, network access, firewall permission, and valid TLS settings.

Configuration

VariableRequiredDescription
DATABASE_URLYesSQLAlchemy connection URL. Treated as a secret by the registry manifest.
DATABASE_SCHEMANoDefault schema or catalog namespace. Recommended for PostgreSQL. Locked against tool overrides in production.
ALLOWED_TABLESProductionComma-separated, case-sensitive table and view allowlist. Production mode refuses to start without it.
SECURE_SCHEMA_ENVNoSet to production or prod for strict startup validation. Defaults to development.
FASTMCP_CHECK_FOR_UPDATESNoSet to off for predictable stdio startup.
FASTMCP_SHOW_SERVER_BANNERNoSet to false to suppress the startup banner.
Multiple schemas

DATABASE_SCHEMA selects the default namespace. Resolution works as follows:

  • In production, a configured DATABASE_SCHEMA is a security boundary and tool arguments cannot override it.
  • Outside production, an explicit tool schema argument overrides DATABASE_SCHEMA.
  • Without either value, the database driver's default schema is used.

For strict production access to multiple schemas, run one MCP server entry per schema with its own DATABASE_SCHEMA and ALLOWED_TABLES values. The table allowlist contains unqualified names, not schema.table values.

Tools

  • schema_overview: compact map of permitted tables, views, primary keys, and foreign-key relationships
  • list_tables: permitted table and view inventory
  • inspect_table: columns, SQL types, nullability, primary keys, unique constraints, and foreign keys for one entity

Every tool defaults to format="compact" for lower token usage:

tables:orders,users | pk:orders(order_id);users(user_id) | fk:orders.user_id->users.user_id

Pass format="markdown" when a human-readable table is more useful.

Security notes

  • The server exposes only SQLAlchemy inspection operations; it provides no row-query or write tool.
  • Missing and disallowed table names return the same message when an allowlist is active, avoiding an existence leak.
  • Client-facing errors are sanitized. Operational details are written to server stderr.
  • The IDE launches the MCP process and supplies its environment, so treat the IDE and its configuration as trusted.
  • Do not commit configurations containing credentials. For stronger isolation, launch through a wrapper that obtains DATABASE_URL from an OS keychain or secret manager.
  • Use a dedicated least-privilege database account and TLS certificate verification for remote connections.

Example PostgreSQL role:

CREATE ROLE schema_reader LOGIN PASSWORD 'use-a-secret-manager';

GRANT CONNECT ON DATABASE appdb TO schema_reader; GRANT USAGE ON SCHEMA public TO schema_reader;

Metadata visibility varies by PostgreSQL provider and database policy. Grant only the additional catalog or object privileges required for inspection; avoid granting row SELECT unless your environment requires it.

Troubleshooting

The server exits immediately

Check the IDE's MCP logs. DATABASE_URL is mandatory, and production mode also requires a non-empty ALLOWED_TABLES value.

No tables or views are discovered

Confirm DATABASE_SCHEMA, exact table-name casing, database permissions, and whether the allowlist contains the expected names.

The connection URL fails with a valid password

Percent-encode reserved URL characters or use a secret-injection wrapper. Do not paste real credentials into issues or logs.

`uvx` is not found

Install uv using its official instructions, or install the package with pipx and use mcp-secure-schema as the command.

Starting the command appears to hang

That is normal for a stdio MCP server. It waits for an MCP client on standard input and is normally started by the IDE.

Development

Clone the repository only when developing or testing the server:

git clone https://github.com/Siddharth-coder13/secure_schema_mcp.git

cd secure_schema_mcp uv sync --extra dev uv run python tests/demo_database.py DATABASE_URL="sqlite:///$PWD/test_schema.db" uv run mcp-secure-schema

Run the test suite:

uv run pytest

Run the opt-in PostgreSQL integration test against a disposable database. The test creates and removes a randomly named schema:

POSTGRES_TEST_DATABASE_URL='postgresql+psycopg2://user@localhost:5432/testdb' \

uv run pytest tests/test_postgres_smoke.py -v

The tests verify row-data isolation, allowlist behavior, sanitized errors, compact output, relationships, schema selection, and the locked production namespace.

Release checklist

Maintainers should update the matching versions in pyproject.toml and server.json, run the complete SQLite and PostgreSQL suites, build with uv build --no-sources, verify installation from the wheel, publish to PyPI, and only then publish server.json to the MCP Registry.

License

Licensed under the Apache License 2.0. See LICENSE and NOTICE.

问 PopNx