MCP server that pools free tiers of multiple LLM providers behind an OpenAI-compatible endpoint, enabling model routing, failover, and usage tracking through tools like tokenmax, capacity, and benchmark.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.BUN_BINFREELLMPOOL_PROXY_KEY— or passed --api-key; Tailnet/LAN serving requires aFREELLMPOOL_PROXY_URLFREELLMPOOL_TOASTFREELLMPOOL_DATA_DIRFREELLMPOOL_RUN_RECORDS_PATHFREELLMPOOL_REPORT_DIRFREELLMPOOL_CACHE_PATHFREELLMPOOL_CACHE_MAX_ENTRIES— WAL mode and TTL pruning; caps retained rowsFREELLMPOOL_CAPABILITY_FILEFREELLMPOOL_EXTERNAL_CATALOG_PATHFREELLMPOOL_CONFIGFREELLMPOOL_AA_API_KEY— () — its Intelligence Index covers most current andFREELLMPOOL_CONFORMANCE_KEYS_JSONFREELLMPOOL_ALLOW_LOCAL_PROVIDERSFREELLMPOOL_JOBS_PATH— ). The queue is foreground-only: jobs run processesFREELLMPOOL_KEYS_PATHFREELLMPOOL_CONFIG_FILEFREELLMPOOL_PUBLIC_BADGE— /badge.svg and /summary.svg live when =1 makesFREELLMPOOL_QUOTA_PATHFREELLMPOOL_QUOTA_FLUSH_EVERY— processes can reduce file churn with =N, whichFREELLMPOOL_STATS_PATHFREELLMPOOL_TASK_EVIDENCE_FILE[](https://m8ven.ai/mcp/0xzr-freellmpool-1j3h4f)