A proxy-aware MCP server that enables web searching across multiple engines and automated markdown content extraction from webpages. It features a deep research agent for recursive searching and synthesis, supporting complex network environments through SOCKS5 and HTTP proxies.
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.ALLOWED_HOSTSBROWSER_CONCURRENCYBROWSER_IDLE_TIMEOUT_MSBROWSER_SCREENSHOT_MAX_SIZECHROMIUM_EXECUTABLE_PATHCORS_ORIGIN— Allowed CORS origin.DEEP_SEARCH_MAX_CITATION_URLS— 10 Max URLs to visit for citations.DEEP_SEARCH_MAX_LOOPS— 20 Max research iterations.DEEP_SEARCH_REPORT_RETENTION_MINUTES— 10 Download expiration time (minutes).DEEP_SEARCH_RESULTS_PER_ENGINE— 5 Results per engine per round.DEEP_SEARCH_SATURATION_THRESHOLD— 0.6 Threshold to stop research early.DEFAULT_SEARCH_ENGINES— bing,duckduckgo,brave Default engines list.DOCKER_ENVIRONMENTENABLE_CORS— false Enable CORS.ENABLE_DNS_REBINDING_PROTECTIONENABLE_PROXY— false Enable proxy support.HTTPS_PROXY— HTTPS Proxy URL.HTTP_PROXY— HTTP Proxy URL.LLM_API_KEY— External LLM API key.LLM_BASE_URL— External LLM API base URL.LLM_NAME— External LLM model name.LLM_RETRY_DELAYSLLM_TIMEOUT_MS— 30000 Timeout for external LLM calls.MCP_LOG_PATHPORT— 3000 Server port.PUBLIC_URL— URL Configuration: Link generation depends on the variable to ensure accessible download endpoints in proxied environments.SAMPLING— false Enable result sampling.SKIP_COOLDOWNSKIP_IDE_SAMPLING— false Prefer external API over IDE.SOCKS5_PROXY— SOCKS5 Proxy URL (Highest Priority).WRITE_DEBUG_FILE— false Log debug output to file.WRITE_DEBUG_TERMINAL— false Log debug output to stdout.[](https://m8ven.ai/mcp/rinaldowouterson-mcp-open-webresearch-07vlrk)