Free-first web search MCP with zero-key English and Chinese sources and compact evidence.
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.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
yaml is vulnerable to Stack Overflow via deeply nested YAML collections
process.env. You'll be asked to provide them before it can run.ALLOWED_ENGINES— / DENIED_ENGINES all / none Engine execution allowlist and denylist; deny winsALLOWED_ORIGINS— match . See the [HTTP deployment guide](./docs/http-deployment.md)BOCHA_API_KEY— Bocha Web Search zh, en Optional Chinese-first AI SearchBRAVE_API_KEY— Brave Search en, zh Optional commercial Web SearchCORS_ORIGINDEDUP_MODELDEDUP_THRESHOLD— Enable optional semantic processing SEMANTIC_DEDUP, SEMANTIC_RERANK, , RERANK_TOP_KDEFAULT_ENGINEDENIED_ENGINES— ALLOWED_ENGINES / all / none Engine execution allowlist and denylist; deny winsDISABLED_TOOLS— ENABLED_TOOLS / all / none Tool registration allowlist and denylist; deny winsENABLED_TOOLS— / DISABLED_TOOLS all / none Tool registration allowlist and denylist; deny winsENABLE_CORSEXA_API_KEY— Exa Search en, zh Optional neural SearchHTTP_ALLOW_UNAUTHENTICATED— true. Browser requests with an Origin header mustHTTP_AUTH_TOKEN— HTTP mode requires unless you setLIVE_E2ELLM_JUDGE_API_KEYLLM_JUDGE_BASE_URLLLM_JUDGE_MODELLOG_LEVELMAX_FULL_RESULTS— Reduce response tokens OUTPUT_STYLE=compact, , SNIPPET_LENGTH, EVIDENCE_BUDGET_CHARSMIN_CONFIDENCEMIN_SOURCE_COUNTMODE— HTTP_AUTH_TOKEN=change-me =http npx agent-search-mcpOPENAI_API_KEYOPENCODE_API_KEYOUTPUT_STYLE— Reduce response tokens =compact, MAX_FULL_RESULTS, SNIPPET_LENGTH, EVIDENCE_BUDGET_CHARSPAID_ENGINE_ORDER— brave,exa,tavily,youcom,tencent_wsa,bocha,serper Selects the first configured optional provider; not a quality claimPORTPROVIDER_COOLDOWN_STORE_PATHPROXY_URL— Use an explicit proxy DUCKDUCKGO_PROXY_URL, SOGOU_PROXY_URL, or USE_PROXY=true withRERANK_MODELRERANK_TOP_K— Enable optional semantic processing SEMANTIC_DEDUP, SEMANTIC_RERANK, DEDUP_THRESHOLD,SEARCH_CACHE_DIRECTORY— Persist the exact-result cache , SEARCH_CACHE_TTL_MS, SEARCH_CACHE_MAX_ENTRIESSEARCH_PROVIDER_MODE— free_first Default routing: free_first, quality_escalation, paid_first, or free_onlySEMANTIC_DEDUP— Enable optional semantic processing , SEMANTIC_RERANK, DEDUP_THRESHOLD, RERANK_TOP_KSEMANTIC_RERANK— Enable optional semantic processing SEMANTIC_DEDUP, , DEDUP_THRESHOLD, RERANK_TOP_KSERPER_API_KEY— Serper Google Search en, zh, auto Optional Google SERP SearchSNIPPET_LENGTH— Reduce response tokens OUTPUT_STYLE=compact, MAX_FULL_RESULTS, , EVIDENCE_BUDGET_CHARSTAVILY_API_KEY— Tavily Search en, zh Optional agent-oriented SearchTENCENT_WSA_API_KEY— Tencent Web Search API zh Optional official Chinese Web SearchUSE_PROXY— Use an explicit proxy DUCKDUCKGO_PROXY_URL, SOGOU_PROXY_URL, or =true with PROXY_URLYDC_API_KEY— You.com Search en, zh Optional commercial Web Search[](https://m8ven.ai/mcp/lennney-agent-search-mcp-10e1yq)