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.

DimensionAiven MCP ServerManage the Aiven cloud data platform from your AI assistantMCP Toolbox for DatabasesGoogle's official database MCP toolbox — define AI-accessible database tools via config
FMRS64 / 100 · C74 / 100 · B
Reliability10 / 2013 / 20
Security and permissions11 / 2013 / 20
Maintenance13 / 2017 / 20
Documentation16 / 2016 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers and ops teams already on Aiven who want AI-assisted resource management
  • Teams managing both PostgreSQL and Kafka
  • Security-conscious users who want a reduced tool surface (read-only, scoped)
  • 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 not on the Aiven platform
  • Production environments where AI agents must not perform destructive actions (dropping databases, deleting services)
  • Self-hosted/local deployments, which cannot use the aiven_docs_search tool
  • 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
  • Local stdio mode requires an Aiven API token (AIVEN_TOKEN)
  • Remote mode uses OAuth authorization; access is governed by the Aiven user permissions of the authenticated account
  • The server can only perform actions the Aiven user is allowed to do
  • 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
  • AI agents may execute destructive actions (dropping databases, deleting services, producing messages) based on their interpretation of prompts
  • With AIVEN_ALLOW_SECRETS enabled, the connection-info tool returns live credentials (passwords, connection URIs, certs) into the conversation
  • Review agent behavior, perform a risk assessment, and follow your organization's security policies before using in production
  • 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 Code, Cursor, VS CodeClaude Code, Gemini CLI, Zed, Antigravity
Tools460