M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionNeon MCP ServerInteract with your Lakebase Postgres databases on Neon using natural language.MCP Toolbox for DatabasesGoogle's official database MCP toolbox — define AI-accessible database tools via config
FMRS73 / 100 · B74 / 100 · B
Reliability8 / 2013 / 20
Security and permissions16 / 2013 / 20
Maintenance18 / 2017 / 20
Documentation17 / 2016 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers and non-developers who want to manage Neon databases via natural language.
  • Users who want to perform database tasks quickly within IDEs or chat interfaces.
  • Teams needing safe migrations and query optimization.
  • Teams that want precise control over which database operations an AI can perform, rather than open arbitrary SQL execution
  • Scenarios needing a unified MCP setup across multiple database engines
Not for
  • Production environments requiring fine-grained control.
  • Users needing a full SQL interface and complex transaction handling.
  • Users who want to run fully offline or without depending on remote services.
  • Lightweight cases that just want to run a few ad-hoc SQL queries without maintaining a tools.yaml config (a simpler single-database MCP may be a better fit)
Required permissions
  • Neon account and authentication (OAuth or API key).
  • Access, create, modify, and delete Neon projects, branches, databases, and resources.
  • Execute SQL queries (read/write).
  • Manage authentication and Data API configurations.
  • Read logs and documentation index.
  • Database credentials (username/password/connection string) are supplied via env vars or config
  • A tool's actual permission is whatever SQL statement is defined in tools.yaml — designed for least privilege, but misconfiguration can still over-expose access
Risks and side effects
  • Natural language requests may accidentally execute destructive operations (e.g., deleting projects or branches).
  • Unauthorized individuals may access your account via API key or OAuth.
  • Production use carries risk of accidental changes; official recommendation is for local development only.
  • Careful review of LLM-proposed actions is required.
  • If tools.yaml defines SQL statements that allow unconstrained writes or deletes, the AI could accidentally modify data
  • The prebuilt toolsets (--prebuilt) favor convenience and may expose broader query capability than a specific business actually needs — use a custom tools.yaml in production
Supported clientsClaude Desktop, Cursor, VS Code, Claude Code, KiroClaude Code, Gemini CLI, Zed, Antigravity
Tools340