Add Styx and Acheron to Community Servers

[timmx7]

Why Styx?

Every AI app hardcodes a specific model and overpays for simple queries. Styx solves this at the gateway level.

What makes it different

Styx is the first MCP server that doesn't just proxy requests — it intelligently routes them. Send model: "styx:auto" and a 9-signal classifier analyzes your prompt in real-time:

• Simple "what's 2+2?" → routes to gpt-4o-mini ($0.15/1M tokens)
• Complex "refactor this distributed system" → routes to gpt-5.4

This saves 60-80% on AI costs with zero code changes.

Key features

• styx:auto — 9-signal prompt classifier (<1ms overhead, Go)
• 65+ models across OpenAI, Anthropic, Google, Mistral
• Auto-failover — provider goes down, traffic reroutes automatically
• Self-hosted — git clone && ./setup.sh && docker compose up
• Dashboard — real-time cost, latency, and request tracking
• MCP-native — npx styx-mcp-server works with Claude Code and Cursor

Links

• GitHub: https://github.com/timmx7/styx
• npm: https://www.npmjs.com/package/styx-mcp-server
• MCP Registry: io.github.timmx7/styx-mcp-server
• License: Apache 2.0

[olaservo]

Thanks for contributing to the MCP servers repo!

We've retired the third-party server list from the README in favor of the MCP Registry — see #3950 for context. The Official Integrations and Community Servers sections no longer exist in the README, so this PR no longer has a target.

Going forward, please publish your server to the MCP Registry using the quickstart guide:
https://github.com/modelcontextprotocol/registry/blob/main/docs/modelcontextprotocol-io/quickstart.mdx

That's where server discovery now happens. Thanks for building on MCP!

---

Note: I'm working through the backlog with help from Claude Code to give everyone a prompt response.