Gateway: MCP server, setup and security

What Gateway does

According to its repository: “Automatically generate APIs from database schema and data for PostgreSQL, ClickHouse, MySQL, Snowflake, BigQuery and Supabase.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Gateway is listed under Databases, a category of 138 servers in the directory, where it ranks #30 by stars.

Topics declared by the repository: api, clickhouse, openai, postgresql, rest-api, snowflake.

Installing and connecting Gateway

No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Go. Listed systems: macOS, Windows.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Gateway:

• Maintenance: no commit for 15 months. Possible flaws and protocol changes are no longer tracked.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on February 10, 2025, the centralmind/gateway repository has 548 stars and 64 forks, with 15 open issues. It has more stars than 88% of the servers in the directory. Last change 15 months ago.

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.