Supabase
MCP server for interacting with the Supabase platform
作者提供的说明(英文原文)
SQLite MCP server with OAuth 2.1, HTTP/SSE, 122 tools, and smart tool filtering
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": {
"db": {
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add db -- npx -y db-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"db": {
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}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": {
"db": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}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 neverinfamous 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(1.0.2)于9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 Node.js, Docker。
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。
SQLite MCP Server with 170+ specialized tools, 11 data resources + 11 help resources, and 10 prompts, audit logging with DDL backup snapshots, HTTP/SSE Transport, OAuth 2.1 authentication, tool filtering, granular access control, and structured error handling with categorized, actionable responses. Available in WASM and better-sqlite3 variants.
[Wiki](https://github.com/neverinfamous/db-mcp/wiki) • [Changelog](CHANGELOG.md)
| Feature | Description |
|---|---|
| 181+ Specialized Tools | The most comprehensive SQLite MCP server available — core CRUD, JSON/JSONB, FTS5 full-text search, statistical analysis, vector search, geospatial/SpatiaLite, introspection, migration, and admin |
| Deep Observability | Built-in Prometheus /metrics export, real-time sqlite://metrics MCP resource, historical persistence to a SystemDb sidecar, and a granular sqlite_audit_search tool for compliance and investigation |
| Dynamic Configuration | Full YAML/JSON config file support (--config) with precedence rules, plus a sqlite_server_config tool for live runtime config updates (e.g., log levels) without server restarts |
| Advanced Query & Search | O(1) cursor-based keyset pagination, faceted search aggregation, and sqlite_hybrid_search orchestrating FTS5 + Vector similarity with Reciprocal Rank Fusion (RRF) in a single tool call |
| AI Index Recommendations | sqlite_index_audit automatically analyzes EXPLAIN QUERY PLAN responses to suggest optimized composite and partial indexes based on workload patterns |
| Real-time Subscriptions | Native resources/subscribe support pushing event-driven notifications for sqlite://schema DDL changes and periodic sqlite://health updates directly to clients |
| 22 Resources | 11 data resources (schema, tables, table_schema, indexes, views, health, meta, audit, metrics, compile_options, pragma) + 11 help resources (sqlite://help + per-group reference) — filtered by --tool-filter |
| 10 AI-Powered Prompts | Guided workflows for schema exploration, query building, data analysis, optimization, migration, debugging, and hybrid FTS5 + vector search |
| Code Mode | Massive Token Savings: Execute complex, multi-step operations inside a V8 isolate sandbox with process-level isolation and hard timeouts. Instead of spending thousands of tokens on back-and-forth tool calls, Code Mode exposes all 180+ capabilities locally, reducing token overhead by 70–90% and supercharging AI agent reasoning |
| Token-Optimized Payloads | Every tool response is designed for minimal token footprint with _meta.tokenEstimate on every response so agents know their token cost. Tools include compact, nodesOnly, maxOutliers, minSeverity, and maxInvalid parameters where applicable — letting agents control response size without losing data access |
| Dual SQLite Backends | WASM (sql.js) for zero-compilation portability, Native (better-sqlite3) for high-performance concurrent execution with full features including transactions, window functions, and SpatiaLite GIS |
| OAuth 2.1 + Access Control | Enterprise-ready security with RFC 9728/8414 compliance, granular scopes (full, read, write, admin, db:*, table:*:*), and Keycloak integration |
| Smart Tool Filtering | 10 tool groups + 7 shortcuts let you stay within IDE limits while exposing exactly what you need |
| HTTP Streaming Transport | Streamable HTTP (/mcp) for modern clients + legacy SSE (/sse) for backward compatibility — both protocols supported simultaneously with security headers, rate limiting, health check, and stateless mode for serverless |
| Production-Ready Security | SQL injection protection (parameterized queries + Unicode-normalized WHERE clause validation), sandboxed code execution (V8 codeGeneration restrictions, frozen prototypes, 29 blocked patterns, Proxy nullified, RPC allowlist), CORS deny-all default, fail-closed scope enforcement, JWT claims sanitization, 7 security headers, body size limits, rate limiting with Retry-After, slowloris timeouts, trustedProxyIps, opt-in HSTS, non-root Docker, and build provenance |
| Encryption at Rest | Native SQLCipher support via --encryption-key or DB_ENCRYPTION_KEY. Dynamically loads better-sqlite3-multiple-ciphers and automatically encrypts the sidecar SystemDb audit logs to prevent sensitive queries from leaking |
| Strict TypeScript | 100% type-safe codebase with strict mode, no any types, 1911 unit tests + 1136 E2E tests and 90% coverage |
| Deterministic Error Handling | Every tool returns structured {success, error, code, category, suggestion, recoverable} responses — no raw exceptions, no silent failures. Agents get enriched error context with actionable suggestions instead of cryptic SQLite codes
只显示了开头部分;其余内容请在仓库中阅读