db-mcp-server
Enables AI assistants to run SQL queries on PostgreSQL databases through a credential-isolated proxy, with read-only queries by default and write operations requiring explicit confirmation.
README
db-mcp-server
A local MCP server that gives an AI coding assistant (e.g. Claude Code) credential-isolated access to your PostgreSQL databases. The assistant sends only SQL and receives only rows — database usernames, passwords, and SSH keys never enter the model's context or the conversation transcript.
Why
Wiring an AI assistant to a database usually means putting connection strings and passwords somewhere the model (and its transcript) can read them. This server keeps that boundary: it owns the encrypted credentials and the SSH tunnels, exposes a small SQL-only tool surface, and defaults to read-only.
How it works
- Catalog (
registry.yaml) — non-secret routing. Organized ascustomers → environments → services; each service maps to a database name and asecret_ref(a pointer into the vault — never a credential). - Vault (
vault.enc) — AES-256-GCM with a scrypt-derived key. Holds the DB credentials, decrypted into memory once at launch using a passphrase. - Tunnel pool — one SSH tunnel per
(customer, environment)viasshtunnel, bound to an ephemeral127.0.0.1port. - Executor —
psycopg.run_queryruns in a Postgres READ ONLY transaction (the engine rejects any write);run_write_queryrequiresconfirm=true.
Install
python -m venv .venv
# Windows PowerShell: .venv\Scripts\Activate.ps1 (bash: source .venv/Scripts/activate)
pip install -e ".[dev]"
Configure
Configuration comes from environment variables; defaults resolve relative to the project root.
| Variable | Purpose | Default |
|---|---|---|
DB_MCP_PASSPHRASE |
Vault passphrase (required to run the server) | — |
DB_MCP_REGISTRY |
Path to registry.yaml |
./registry.yaml |
DB_MCP_VAULT |
Path to vault.enc |
./vault.enc |
DB_MCP_KEYS_DIR |
Directory holding the SSH PEM keys | ./keys |
DB_MCP_BOOTSTRAP |
Path to bootstrap.yaml |
./bootstrap.yaml |
Provision (first-time setup)
- Copy the template and fill in real values:
cp bootstrap.example.yaml bootstrap.yaml - Put your SSH private keys in
keys/(filenames must match thepem_keyfields in the catalog). - Generate the non-secret catalog and the encrypted vault (prompts for the
passphrase you'll reuse to run the server):
python -m db_mcp_server.bootstrap --dry-run # preview, writes nothing python -m db_mcp_server.bootstrap # writes registry.yaml + vault.enc python -m db_mcp_server.vault_admin verify # expect {"ok": true}
bootstrap.yaml holds plaintext credentials — it is git-ignored; delete it
or keep it offline once the vault exists.
Command-line tools
| Command | Purpose |
|---|---|
db-mcp-server |
The MCP server (stdio). Launched by the MCP client, not by hand. |
db-vault |
Manage credentials in the vault: set / rm / list / verify. |
db-bootstrap |
Split bootstrap.yaml into registry.yaml + vault.enc. |
(Console commands exist after pip install -e .; the python -m db_mcp_server.<module>
form always works.)
Tools exposed to the assistant
list_databases()— the catalog (customers → environments → services); no secrets.run_query(customer, environment, service, sql, max_rows?)— read-only.run_write_query(customer, environment, service, sql, confirm)— gated write.
Domain failures come back as a structured {error_code, message} rather than an
exception, so the assistant can react.
Register with an MCP client
Example .mcp.json (adjust paths). Use ${DB_MCP_PASSPHRASE} so the passphrase
is read from the shell instead of being written into the file:
{
"mcpServers": {
"db": {
"command": "/absolute/path/to/db-mcp-server/.venv/Scripts/python.exe",
"args": ["-m", "db_mcp_server.server"],
"env": {
"DB_MCP_PASSPHRASE": "${DB_MCP_PASSPHRASE}"
}
}
}
}
Security notes
vault.enc,keys/,bootstrap.yaml,*.env, and*.pemare git-ignored — never commit them.- The vault passphrase is supplied via
DB_MCP_PASSPHRASE(or a prompt) — never stored inregistry.yaml, argv, or logs. db-vaultreads the DB password via a hidden prompt (getpass), never via argv.run_queryis read-only at the Postgres engine level; writes requireconfirm=true.
Tests
pip install -e ".[dev]" && python -m pytest -q
The DB integration test is skipped unless DB_MCP_TEST_DSN points at a reachable
PostgreSQL.
Roadmap (not in this build)
Persistent audit trail, multi-user operation, external secret-manager backing, schema-introspection tools, and a permission denylist to turn the credential isolation into a hard boundary.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。