$ loading_
Access multiple LLM providers via MCP with routing, quotas, and usage stats.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "freellmpool" MCP server from askskill: Run: claude mcp add 'io-github-0xzr-freellmpool' -- uvx freellmpool
Using freellmpool, list available models and answer the same question with speed-first and quality-first strategies: summarize the key points of this technical document.
A list of available models plus two responses generated with different routing strategies.
Using freellmpool, check quotas, token usage, and recent usage stats for each provider, then identify which provider is closest to its limit.
A summary of provider quotas and usage statistics, highlighting any limit risks.
Using freellmpool, choose an appropriate model and run this task under a per-request limit of 8000 tokens with cost efficiency prioritized: compare the strengths and weaknesses of three competitor proposals.
The selected model or provider, the routing rationale, and the completed analysis.
Unify multiple LLM providers, routing, and model collaboration in one local gateway.
Delegate low-risk tasks to a cheaper model with main-agent review.
Route LLM requests across providers and orchestrate MCP tools with local privacy.
Build, debug, and manage software tasks with natural language across LLMs.
Access multiple LLM providers through one encrypted OpenAI-compatible gateway.
Access multiple AI providers in one terminal for generation, search, and comparison.