multi-llm-mcp-server — Claude Code skill: features and install
The multi-llm-mcp-server skill connects Claude Code with Codex CLI and multiple language models. Use it to compare parallel model responses or hand code analysis to Codex.
no license 107 installs ★ 9 updated 2026-10-09
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a claude-codeWhat multi-llm-mcp-server does
The skill guides Claude Code in sending a prompt to one model or several at once, then comparing the results. Multiple models can inspect the same code with a shared instruction. Sessions let you continue a conversation with a chosen model, review active sessions, or clear them.
The MCP server requires Python 3.10+, the fastmcp and openai packages, and API keys for the providers you plan to use. Its ask_codex and wait_codex tools connect to Codex CLI. In read-only mode Codex can inspect files without changing them; workspace-write allows edits inside the workspace. Codex CLI must be installed, authenticated, and available on PATH for those tools to run.
The skill covers server setup and tools for checking configured providers and waiting on longer jobs. Claude requires a manual change to LLM_MIX.py and an ANTHROPIC_API_KEY; until enabled, that provider is not available through the server.
What it helps with
- Compare several models' answers to one prompt
- Ask multiple models to review the same code
- Have Codex CLI inspect a project's structure
- Delegate workspace file edits to Codex CLI
- Check which model providers are configured
Example prompts for the agent
- Compare GPT, DeepSeek, and Qwen on whether this project should use a monorepo or separate repositories.
- Review this code for security issues using multiple models.
- Ask Codex CLI to find every TODO comment in the project without changing files.
How to install multi-llm-mcp-server
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a claude-code2Manually: put the files in place
~/.claude/skills/multi-llm-mcp-server/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/multi-llm-mcp-server/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a codex2Manually: put the files in place
.agents/skills/multi-llm-mcp-server/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a cursor2Manually: put the files in place
.cursor/skills/multi-llm-mcp-server/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/mcp-skills skills/multi-llm-mcp-server2Manually: put the files in place
.github/skills/multi-llm-mcp-server/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/multi-llm-mcp-serverManually: put the files in place
.devin/skills/multi-llm-mcp-server/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about multi-llm-mcp-server
How do I install multi-llm-mcp-server in Claude Code?
Run npx skills add reason-machines/mcp-skills --skill multi-llm-mcp-server -a claude-code. The skill file is placed at ~/.claude/skills/multi-llm-mcp-server/SKILL.md.
What does multi-llm-mcp-server do?
It lets Claude Code query individual models or send a prompt to several models in parallel. The skill also covers delegating tasks to Codex CLI and managing model conversation sessions.
What do I need to use Codex CLI with this skill?
Install Codex CLI, authenticate it, and make sure codex is available on PATH. Use read-only for analysis without edits or workspace-write for changes within the workspace.