Supabase
Supabase’s official server lets AI create tables, query data and review project settings in your Supabase database.
Description from the maker (original English)
SQLite MCP server with OAuth 2.1, HTTP/SSE, 122 tools, and smart tool filtering
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"db": {
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}Run this in your terminal
claude mcp add db -- npx -y db-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"db": {
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"db": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"db-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account neverinfamous, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 9 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Supabase, MongoDB MCP Server, Elasticsearch MCP Server
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Supabase’s official server lets AI create tables, query data and review project settings in your Supabase database.
MongoDB Model Context Protocol Server
MCP server for interacting with Elasticsearch
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
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
Only the beginning is shown; read the rest in the repo