mcp-datalink
MCP server for secure database access (PostgreSQL, MySQL, SQLite)
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"@pilat/mcp-datalink": {
"args": [
"@pilat/mcp-datalink@1.2.4"
],
"command": "npx"
}
}
}可用工具 （5 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
tavily_search 14 个参数 需填 1 项
Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.
必填参数：query
tavily_extract 6 个参数 需填 1 项
Extract content from URLs. Returns raw page content in markdown or text format.
必填参数：urls
tavily_crawl 11 个参数 需填 1 项
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
必填参数：url
tavily_map 8 个参数 需填 1 项
Map a website's structure. Returns a list of URLs found starting from the base URL.
必填参数：url
tavily_research 2 个参数 需填 1 项
Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources to answer a question or complete a task. Returns a detailed response based on the research findings.
必填参数：input
服务介绍
@pilat/mcp-datalink
MCP server for PostgreSQL, MySQL, and SQLite. Gives AI assistants secure database access via Model Context Protocol.
npx @pilat/mcp-datalink
Works with Claude Desktop, Claude Code, Cursor, Cline, and any MCP-compatible client.
# Installation
Add to your MCP client config file (see [config locations](# config-file-locations) below):
{
"mcpServers": {
"datalink": {
"command": "npx",
"args": ["-y", "@pilat/mcp-datalink"],
"env": {
"DATALINK_ANALYTICS_URL": "postgresql://user:password@localhost:5432/analytics",
"DATALINK_ANALYTICS_READONLY": "true",
"DATALINK_INVENTORY_URL": "mysql://user:password@localhost:3306/inventory",
"DATALINK_CACHE_URL": "sqlite:///path/to/cache.db"
}
}
}
}
This creates three database connections: analytics (read-only), inventory, and cache.
| Variable | Description |
|- -- -- -- -- -|- -- -- -- -- -- --|
| DATALINK_{NAME}_URL | Connection URL (creates database named {name}) |
| DATALINK_{NAME}_READONLY | Set to true to block writes |
| DATALINK_{NAME}_MAX_TIMEOUT | Max query timeout in ms (caps model requests) |
Connection URL formats:
# PostgreSQL
postgresql://user:password@localhost:5432/dbname
postgresql://user:password@localhost:5432/dbname?sslmode=require
# MySQL
mysql://user:password@localhost:3306/dbname
mysql://user:password@localhost:3306/dbname?ssl=true
# SQLite
sqlite:///path/to/database.db
sqlite:///Users/me/data/app.sqlite
sqlite://../relative/path/data.db
# # Environment Variable Substitution
URLs support ${VAR} syntax to reference other environment variables:
{
"mcpServers": {
"datalink": {
"command": "npx",
"args": ["-y", "@pilat/mcp-datalink"],
"env": {
"DATALINK_MAIN_URL": "${DATABASE_URL}"
}
}
}
}
This allows reusing existing environment variables (like DATABASE_URL from your shell or .env file).
Supported syntax:
| Syntax | Description |
|- -- -- -- -|- -- -- -- -- -- --|
| ${VAR} | Expands to value of VAR, or keeps ${VAR} if unset |
| ${VAR:-default} | Expands to value of VAR, or default if unset |
Examples:
# Reference existing DATABASE_URL
DATALINK_MAIN_URL="${DATABASE_URL}"
# Build URL from parts
DATALINK_MAIN_URL="postgresql://${DB_USER}:${DB_PASS}@${DB_HOST}:5432/mydb"
# With default values
DATALINK_MAIN_URL="postgresql://localhost:${DB_PORT:-5432}/mydb"
# # Config File Locations
| Client | Config file |
|- -- -- -- -|- -- -- -- -- -- --|
| Claude Code | ~/.claude.json (global) or .mcp.json (project) |
| Claude Desktop (macOS) | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Claude Desktop (Windows) | %APPDATA%\Claude\claude_desktop_config.json |
| Cursor | ~/.cursor/mcp.json or Settings → Features → MCP Servers |
| Cline | cline_mcp_settings.json or VS Code settings cline.mcpServers |
# Tools
| Tool | Description |
|- -- -- -|- -- -- -- -- -- --|
| list_databases | List configured database connections |
| list_tables | List tables with row counts |
| describe_table | Get schema, indexes, foreign keys |
| query | Run SELECT queries |
| execute | Run INSERT/UPDATE/DELETE |
| explain | Show query execution plans |
# Security
- Prepared statements only (no SQL injection)
- Single statement per query (no chaining)
- DDL blocked (no DROP, ALTER, TRUNCATE)
- Readonly mode per connection
- Output truncation (100 rows, 64KB max)
- Query timeout: 30s default, model can request up to 10min,
MAX_TIMEOUTcaps it
# License
MIT
