My Claude Code
Local multi-provider LLM proxy and router that shares models and routing across coding agents.
Tested on LinuxKnown vulnerabilities
Use it
Before you install: known vulnerabilities
pickfit found 2 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.
crates:quick-xml 0.38.4Quadratic run time when checking a start tag for duplicate attribute names (RUSTSEC-2026-0194, high, fixed in 0.41.0)
See 1 more
crates:quick-xml 0.38.4— RUSTSEC-2026-0195 (high), fixed in 0.41.0
Linux x86_64
You need first
- Runtimes:
Python 3.14
Install via uv tool install my-claude-code
uv tool install my-claude-code
Verified in pickfit: the commands exactly as its sandbox ran them
For the record only: they name the sandbox's home, /home/sbx.
uv tool install my-claude-codemcc-server --versionmcc-servergrep -n "^MODEL" /home/sbx/.mcc/.envCheck that it works
mcc-server --versionThe output should contain “my-claude-code 7.121.0”.
First thing to try
mcc-servergrep -n "^MODEL" "$HOME"/.mcc/.envWhat it does
- Send AI coding agents through one addressNot shown working
- Route models with fallback chainsNot shown working
- Send web searches across search providersNot tested
- Track cost and usage with analyticsNot tested
How far pickfit got
Linux x86_64
- Installs
- Starts
- 0 of 4 features work
- Works offline
Windows and macOS: the project says it runs there; pickfit hasn’t tried it.
Good for
- send Anthropic Messages traffic to cloud, subscription, or local models
- share one set of models, credentials, and fallback chains across agents
- fulfill an agent web_search tool across search providers
- log, price, and search requests afterwards
- put Ollama, LM Studio, or llama.cpp behind the same address
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
Its service answers requests
- Replayed from scratch
- Works offline
- Checked on 30 Oct 2026
- Version 7.121.0
Differences the test machine hit
- README: MCC requires Python 3.14 and pip will refuse on anything older
In the test: uv automatically provisioned isolated Python 3.14 and install succeeded on system Python 3.12