Skip to Content
prxy.monster v1 is in early access. See what shipped →
IntegrationsUsing prxy.monster with Claude Code

Using prxy.monster with Claude Code

This is the headline integration. If you’re paying $200/mo for Claude Code and getting 45 productive minutes before MCP overhead + rate limits + auto-compaction force you to restart — this is the fix.

Setup time: 30 seconds.

Configure

export ANTHROPIC_BASE_URL=https://api.prxy.monster export ANTHROPIC_API_KEY=prxy_live_xxxxxxxxxxxxxxxxxxxxxxxx

Restart Claude Code. That’s it.

Claude Code uses @anthropic-ai/sdk under the hood. It respects ANTHROPIC_BASE_URL automatically — no settings change, no config file edit, no restart of anything other than Claude Code itself.

Code change

None. Claude Code is a CLI; you don’t touch its code. Just the two env vars above.

Verify

prxy doctor

(or, if you don’t have the CLI:)

curl https://api.prxy.monster/health

Open Claude Code and watch its first few requests — they’ll succeed if routing works.

What you get

Concretely, on a typical Claude Code session:

PainFix
MCP overhead — ~67k tokens loading every MCP definition before you typemcp-optimizer — prunes irrelevant tools per query. ~67k → ~8k.
Rate limit at 20 minutessemantic-cache returns repeats free. exact-cache catches identical re-asks.
Auto-compaction wipes contextcompaction-bridge preserves the working set across compaction events. rehydrator restores the relevant context on the next message.
Sessions don’t compound — every Monday starts from zeropatterns logs successful fixes and re-injects them. The model gets faster on problem types you’ve solved before.
Long sessions hit context wallipc compresses old messages progressively (verbatim → truncated → summary → single sentence).

This is the killer config:

PRXY_PIPE=mcp-optimizer,compaction-bridge,rehydrator,semantic-cache,patterns,ipc

Set it in the dashboard at app.prxy.monster/keys  under your key’s “Pipeline override” field. Or set per-process:

export PRXY_PIPE=mcp-optimizer,compaction-bridge,rehydrator,semantic-cache,patterns,ipc

(Note: PRXY_PIPE is read by the proxy, not by Claude Code — it goes in the prxy.monster dashboard for cloud, or in the local Docker container for local mode.)

Streaming

Claude Code uses streaming heavily. prxy.monster passes through Anthropic’s per-block SSE format unmodified. Cache hits replay as synthetic SSE, indistinguishable to Claude Code’s parser.

Pricing reality check

You’re already paying Anthropic for tokens. prxy.monster doesn’t add per-token cost — you BYOK to Anthropic, and we charge a flat tier for the gateway.

Net effect for a typical Claude Code user:

  • Anthropic bill: same to slightly lower (cache hits = fewer billed tokens).
  • prxy.monster bill: $0 free tier or $20/mo Pro.
  • Your time: significantly more productive minutes per dollar.

Common issues

  • anthropic-beta headers — pass-through. Prompt caching, tool use, and other beta features all work.
  • MCP servers — Claude Code’s MCP wiring is unaffected. The mcp-optimizer module sees the tool definitions Claude Code sends and prunes irrelevant ones before the request hits Anthropic.
  • /clear — works the same. The patterns module preserves your learned patterns across /clear.
  • Local mode — point ANTHROPIC_BASE_URL=http://localhost:3099 to your local Docker container (see Local quickstart).

Worked example

Drop-in .env and a step-by-step setup walkthrough: github.com/Ekkos-Technologies-Inc/prxy-examples/tree/main/examples/claude-code-setup 

Last updated on