Enables creating and using REST APIs from natural language descriptions, with MCP tools to generate, manage, and interact with deployed API wrappers.
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.XDG_RUNTIME_DIRGATEWAY_PROXY_HOST— 127.0.0.1 Host wrappers are reachable on from the gatewayGATEWAY_API_KEY— Opt-in: unset (default) and the gateway is fully open, as before.HEALTH_SWEEP_INTERVAL— 30 Seconds between registry health sweepsHEALTH_PROBE_TIMEOUT— 2 Per-wrapper /health probe timeout (s)REDIS_URL— unset (in-memory) Job persistence backend; compose sets redis://redis:6379/0. History survives restarts; interrupted jobs are marked failedJOBS_HISTORY_MAX— 200 Terminal jobs kept in history before pruning oldestPROXY_TIMEOUT— 30 Gateway → wrapper proxy timeout (s)MCP_SPEC_TTL— openapi.json (cached s).METRICS_FLUSH_INTERVAL— 30 Seconds between metric flushes to redisNAMELITELLM_BASE_URLLITELLM_API_KEY— (required, no default) Proxy API key — set via .env, never commit itLLM_REQUEST_TIMEOUT— 120 Per-request timeout (s)LLM_MODEL— GLM-5.2 Model id (must match proxy /v1/models)LLM_JSON_MAX_TOKENS— 8000 JSON-mode budget — reasoning models burn hidden thinking tokens against itWRAPPER_OUTPUT_BASE— /tmp/openapi-anything-wrappers Generated wrapper code directoryPIPELINE_MAX_RETRIES— 5 LLM fix-loop attempts before the safe fallbackSEARXNG_BASE_URL— research via a SearxNG instance (, defaultSEARXNG_TIMEOUT— 10 Search request timeout (s)SEARXNG_MAX_RESULTS— 5 Research hits fed into inspection/design[](https://m8ven.ai/mcp/schniggie-openapi-anything-jbtqsa)