M
MCP Directory CURATED DIRECTORY
693 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.

DimensionPostgres MCP ProConfigurable read/write access and performance analysis for PostgreSQL MCPMCP ClickHouseConnect ClickHouse to your AI assistantsMCP Toolbox for DatabasesGoogle's official database MCP toolbox — define AI-accessible database tools via config
FMRS48 / 100 · D79 / 100 · B74 / 100 · B
Reliability9 / 2012 / 2013 / 20
Security and permissions7 / 2018 / 2013 / 20
Maintenance10 / 2017 / 2017 / 20
Documentation11 / 2017 / 2016 / 20
Setup experience11 / 2015 / 2015 / 20
Best for
  • PostgreSQL developers needing deep performance analysis and index tuning
  • DBAs who need read-only access and health checks in production
  • Teams that want AI assistants to help with database optimization and monitoring
  • Teams already using ClickHouse who want AI assistants to access data directly.
  • Scenarios requiring fast, read-only data queries and schema exploration.
  • 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
  • Users needing full write access but wanting safety controls (restricted mode is read-only)
  • Users of non-PostgreSQL databases
  • Users needing real-time monitoring or alerting (this tool is analytical)
  • Scenarios requiring write access to the database without explicit opt-in.
  • Production environments with stringent security requirements that avoid default permission settings.
  • 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
  • Database connection credentials (connection URI)
  • Read-write or read-only database access (depending on access mode)
  • Optional: permission to load extensions (pg_stat_statements, hypopg)
  • Optional: OpenAI API key for experimental LLM index tuning
  • Requires read-only access to ClickHouse database (default).
  • Optional: write access via CLICKHOUSE_ALLOW_WRITE_ACCESS.
  • Optional: destructive operations via CLICKHOUSE_ALLOW_DROP.
  • 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
  • Unrestricted mode can allow SQL that might damage or delete data
  • SQL parsing may not prevent all bypasses of read-only restrictions if unsafe procedural languages are enabled
  • Connection credentials may be stored in plaintext in MCP client configuration
  • Index tuning search may consume significant database resources
  • If write access is enabled, AI might make unintended modifications.
  • If DROP access is enabled, data deletion could occur accidentally.
  • Credentials may be exposed via environment variables.
  • 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, Windsurf, Goose, Qodo GenClaude DesktopClaude Code, Gemini CLI, Zed, Antigravity
Tools940