docs-mcp-server

I'm struggling to find a way for Codex to perform thorough searches without having to pay for a plan or wasting tokens. What I've tried: * Codex's built-in web search tool: can't browse JS-only sites. In my case, it's unable to browse developer.apple.com. * `microsoft/playwright-mcp`: It's able to perform searches and read pages, but very heavy hit on context. Burned through 10% of the context window for a single search. * Exa.ai, context7.com, Brave Search MCP: I'm strongly turned off by the pay-per-thousand model or caps on free plans. I understand they have to make money, it's just not what I want to spend money on. * https://github.com/arabold/docs-mcp-server: I didn't test this, but I was turned off by the fact you have to run the server in the background instead of allowing it to be booted by the Codex instance (via npx) like it can

If you aren't already (1) telling Claude Code which flavor of SQL you want (there are several major dialects and many more minor ones) and (2) giving it access to up-to-date documentation via MCP (e.g. https://github.com/arabold/docs-mcp-server) so it has direct access to canonical docs for authoritative grounding and syntax references, you'll find that you get much better results by doing one or both of those things.