Supabase
MCP server for interacting with the Supabase platform
作者提供的说明(英文原文)
Run alias-based queries against PostgreSQL, MySQL, MongoDB and Oracle without exposing credentials.
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。
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。
选择你使用的 AI 应用,然后复制设置。
你需要
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": {
"custom-database": {
"command": "uvx",
"args": [
"custom-mcp-database"
]
}
}
}在终端中运行这条命令
claude mcp add custom-database -- uvx custom-mcp-database粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"custom-database": {
"command": "uvx",
"args": [
"custom-mcp-database"
]
}
}
}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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"custom-database": {
"type": "stdio",
"command": "uvx",
"args": [
"custom-mcp-database"
]
}
}
}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。
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。
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7日
注册名称已通过 GitHub 账户 renanlido 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
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。
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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
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)。
GitHub 仓库最后更新于–,最新版本(0.6.2)于5个月前进入注册中心。
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)。
同一分类中有:Supabase, MongoDB MCP Server, Elasticsearch MCP Server
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
MCP server for interacting with the Supabase platform
MongoDB Model Context Protocol Server
MCP server for interacting with Elasticsearch
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。
mcp-name: io.github.renanlido/custom-mcp-database
An MCP server that lets AI agents run alias-based queries against PostgreSQL, MySQL, MongoDB and Oracle — without ever exposing credentials to the model. Connections are configured once and stored locally; the agent only ever references them by alias.
Works with Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Gemini CLI, and any other MCP client (all use the same stdio launch command).
There are two roles, on purpose. Keeping them separate is what stops your DB password from ever reaching the model.
The agent never installs credentials. You do, with the CLI. The secret stays on your machine and is never sent to the model.
Easiest way — the guided wizard (asks type, host, user, and how to supply the secret; optionally tests the connection):
uvx custom-mcp-database setup
Or do it in one line (you'll be prompted for the password — hidden input):
uvx custom-mcp-database add-db --alias prod_ro --type postgres \
--host db.internal --port 5432 --user reporting --dbname app
uvx custom-mcp-database list-aliases # confirm it's there
Point your MCP client at the server (see Install), then just ask:
"Using prod_ro, run
SELECT count(*) FROM orders."
The agent calls db_execute_query with the alias prod_ro — never a host, user, or password. It physically cannot see the credentials; they live in your local config, resolved only inside the server process at query time.
Why the agent can't add the DB: an MCP tool's arguments are produced and read by the LLM. If the agent typed your password into an add tool, that password would land in the model's context, the provider, and the logs. So credential setup is a human/CLI step by design. (Need an agent to wire connections in an automated pipeline? See MCP_DB_ALLOW_ADMIN_TOOLS in SECURITY.md — even then it only accepts a *reference* to a secret, e.g. an env-var name, never the secret itself.)
Writes are off by default (read-only). To allow them for a task: export MCP_DB_READONLY=0 MCP_DB_ALLOW_WRITES=1.
The server runs over stdio. The universal launch command is uvx custom-mcp-database run (requires uv; the package is fetched from PyPI on first run).
# Direct (published package)
claude mcp add custom-mcp-database -- uvx custom-mcp-database run
/plugin marketplace add renanlido/custom-mcp-database /plugin install custom-mcp-database@renanlido-mcp
Two options:
.mcpb (mcpb pack) and open it in Claude Desktop. See Distribution.examples/mcp-clients/claude-desktop.json to claude_desktop_config.json.Copy the matching snippet — all use the same command/args, only the file and key differ:
| Client | Config file | Key | Snippet |
|---|---|---|---|
| Cursor | ~/.cursor/mcp.json | mcpServers | cursor.json |
| VS Code | .vscode/mcp.json | servers | vscode.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | mcpServers | windsurf.json |
| Gemini CLI | ~/.gemini/settings.json | mcpServers | gemini-cli.json |
Full client matrix and a local-checkout variant: examples/mcp-clients/README.md.
Configure connections from your terminal with the CLI — never through the agent. A connection's password is a real secret; if it were passed as an MCP tool argument it would enter the model's context (and the provider, transcripts, and logs). So the credential-management tools are off the MCP surface by default; provisioning is a human/CLI task. The agent only lists and uses aliases.
Omit --password/--uri to be prompted securely (hidden input, not stored in shell history). Even better, keep the secret out of the config file entirely with --password-env / --password-file (resolved at connection time):
# PostgreSQL — prompted for the password (recommended)
uvx custom-mcp-database add-db --alias pg --type postgres \ --host localhost --port 5432 --user me --dbname app
MYSQL_PW=... uvx custom-mcp-database add-db --alias my --type mysql \ --host localhost --port 3306 --user root --dbname app --password-env MYSQL_PW
uvx custom-mcp-database add-db --alias ora --type oracle \ --host db.example.com --port 1521 --user system --dbname ORCLPDB1 \ --password-file /run/secrets/ora_pw
uvx custom-mcp-database add-db --alias mongo --type mongo \ --dbname app --uri-file /run/secrets/mongo_uri
uvx custom-mcp-database list-aliases uvx custom-mcp-database remove-db --alias pg
Config location (override with MCP_DB_CONFIG): $XDG_CONFIG_HOME/custom-mcp-database/mcp_config.sqlite3 (default ~/.config/custom-mcp-database/mcp_config.sqlite3, 0600).
If you pass a literal
--password/--uri, it is stored as plaintext JSON in that
SQLite file. Prefer
--password-env/--password-file(or--uri-env/--uri-file) so
only a reference is stored. Either way, keep the file secret (it is
0600, gitignored,
not encrypted).
| Tool | Purpose |
|---|---|
db_list_aliases | List configured aliases and types |
db_execute_query | Run SQL or a MongoDB JSON filter |
db_list_collections | List MongoDB collections |
db_security_status | Report the active security policy |
db_add_database / db_remove_database are not exposed over MCP by default — manage connections with the CLI. To opt into exposing them (the add tool only accepts secrets by reference, never a literal password), set MCP_DB_ALLOW_ADMIN_TOOLS=1.
db_execute_query notes: SQL runs as given with parameterized binds (add your own LIMIT); MongoDB takes a JSON filter + collection, caps results at 10 (--limit), rejects empty filters, and coerces 24-char hex strings to ObjectId.
This server handles real credentials and production data, so it ships deny-by-default:
;-injection blocked), single statement per call.$where, $function, $accumulator, mapReduce, …).oracle_schema can't be used for injection).MCP_DB_MAX_ROWS (default 1000); secrets redacted from errors.0600 plaintext SQLite — keep the host disk encrypted.Check the live posture: custom-mcp-database security-status (or the db_security_status tool).
Enable writes for a specific task (then turn it back off):
export MCP_DB_READONLY=0
export MCP_DB_ALLOW_WRITES=1 # INSERT/UPDATE/DELETE
Read the full protocol — least-privilege DB roles, TLS, prompt-injection handling, vulnerability reporting — in [SECURITY.md](SECURITY.md). The app-layer guards are defense-in-depth; the authoritative control is a least-privilege database account.
uv sync # create .venv and install deps
make run # run the server (stdio) make lint # ruff make build # sdist + wheel into dist/
Inspect tools interactively:
uv run mcp dev src/custom_mcp_database/server.py
This repo ships ready-to-publish metadata for every major channel. All of it is published automatically on push to main (see below):
| Channel | File | Published by |
|---|---|---|
| PyPI | pyproject.toml | release.yml (push to main) |
| MCP Registry | server.json | release.yml (push to main) |
| Claude Code plugin | .claude-plugin/plugin.json, .mcp.json | available on GitHub push |
| Claude Code marketplace | .claude-plugin/marketplace.json | available on GitHub push |
| Claude Desktop bundle | manifest.json | release.yml attaches .mcpb to the Release |
mainReleases are fully automated. On every push to main, .github/workflows/release.yml:
feat: → minor, BREAKING CHANGE/type!: → major, anything else → patch; add [skip release] to a commit message to skip).pyproject.toml and syncs it into every artifact (server.json, manifest.json, plugin + marketplace) via scripts/sync_version.py — version lives in one place, no hand-bumping.chore(release): vX [skip ci], tags vX, pushes.The release commit carries [skip ci], so it does not re-trigger the workflow.
One-time setup (can't be automated — needs your accounts):
renanlido/custom-mcp-database, workflow release.yml.main (repo → Settings → Actions → *Read and write permissions*; if main is a protected branch, allow the actions bot to bypass or use a PAT).The MCP Registry namespace is io.github.renanlido/custom-mcp-database (GitHub-validated).
Local manual escape hatch: make build (syncs version + builds) then uv publish.
MIT