Default MCP Catalog — Search¶
Web search and content retrieval. Remote services (Tavily, Exa, Firecrawl, Jina AI, SerpAPI) expect a vendor API key via ${VAR} placeholders in the headers; the community stdio entry (Brave Search) needs BRAVE_API_KEY in the env section. All five remote services have a free tier sufficient for tutorial-scale use.
Entries (6)¶
Click any card to expand the full spec inline — transport (Streamable HTTP / STDIO), authentication shape (OAuth 2.1 / API key / Bearer / none), required environment variables, vendor URL or stdio command, and the upstream docs link.
AI-optimised web search and answer engine for grounding LLMs with up-to-date facts and sources. Requires TAVILY_API_KEY.
Vendor Tavily · T1 vendor
Auth API key
Vendor — Tavily (vendor-official (Tier 1))
Transport — Streamable HTTP
URL — https://mcp.tavily.com/mcp
Auth — API key
Stability — GA · Tier — Tier 1
Required env — TAVILY_API_KEY
Tags — global
Description
AI-optimised web search and answer engine for grounding LLMs with up-to-date facts and sources. Requires TAVILY_API_KEY.
Docs: https://docs.tavily.com/documentation/mcp
Neural web search by Exa — semantic ranking, source-aware retrieval, and high-quality result snippets. Requires EXA_API_KEY (x-api-key header).
Vendor Exa · T1 vendor
Auth API key
Vendor — Exa (vendor-official (Tier 1))
Transport — Streamable HTTP
URL — https://mcp.exa.ai/mcp
Auth — API key
Stability — GA · Tier — Tier 1
Required env — EXA_API_KEY
Tags — global
Description
Neural web search by Exa — semantic ranking, source-aware retrieval, and high-quality result snippets. Requires EXA_API_KEY (x-api-key header).
Docs: https://exa.ai/docs/reference/exa-mcp
Web scraping, crawling, and structured data extraction with anti-bot handling. Bearer-authenticated with FIRECRAWL_API_KEY.
Vendor Firecrawl · T1 vendor
Auth Bearer
Vendor — Firecrawl (vendor-official (Tier 1))
Transport — Streamable HTTP
URL — https://mcp.firecrawl.dev/v2/mcp
Auth — Bearer
Stability — GA · Tier — Tier 1
Required env — FIRECRAWL_API_KEY
Tags — global
Description
Web scraping, crawling, and structured data extraction with anti-bot handling. Bearer-authenticated with FIRECRAWL_API_KEY.
Docs: https://docs.firecrawl.dev/mcp-server
Jina AI Reader (URL-to-clean-markdown) and search APIs for LLM-grounded retrieval. Bearer-authenticated with JINA_API_KEY.
Vendor Jina AI · T2 vendor
Auth Bearer
Vendor — Jina AI (vendor-official (Tier 1))
Transport — Streamable HTTP
URL — https://mcp.jina.ai/v1
Auth — Bearer
Stability — GA · Tier — Tier 2
Required env — JINA_API_KEY
Tags — global
Description
Jina AI Reader (URL-to-clean-markdown) and search APIs for LLM-grounded retrieval. Bearer-authenticated with JINA_API_KEY.
Docs: https://github.com/jina-ai/MCP
Real-time Google, Bing, Baidu, DuckDuckGo, Naver and other SERP scraping with structured JSON. API key embedded in URL path (SERPAPI_API_KEY).
Vendor SerpAPI · T2 vendor
Auth API key
Vendor — SerpAPI (vendor-official (Tier 1))
Transport — Streamable HTTP
URL — https://mcp.serpapi.com/${SERPAPI_API_KEY}/mcp
Auth — API key
Stability — GA · Tier — Tier 2
Required env — SERPAPI_API_KEY
Tags — global
Description
Real-time Google, Bing, Baidu, DuckDuckGo, Naver and other SERP scraping with structured JSON. API key embedded in URL path (SERPAPI_API_KEY).
Docs: https://github.com/serpapi/serpapi-mcp
[macOS] Brave Search API — web, local, news, image, and video search. Outbound calls only to api.search.brave.com (no SSRF surface). The activated form is pre-filled to run: npx -y…
Vendor Brave · T1 vendor
Auth STDIO
Vendor — Brave (vendor-official)
Transport — STDIO
Command — npx
Args — -y @brave/brave-search-mcp-server
OS variants — mac · linux · win (catalog picks the entry matching the host OS automatically; macOS / Linux use npx or uvx; Windows uses npx.cmd).
Auth — STDIO
Stability — GA · Tier — Tier 2
Required env — —
Tags — global
Description
[macOS] Brave Search API — web, local, news, image, and video search. Outbound calls only to api.search.brave.com (no SSRF surface).
Prereq: Node.js 18+ on macOS (Homebrew, nvm, or installer). Free API key (2k req/month) at https://api.search.brave.com/app/keys.
The activated form is pre-filled to run: npx -y @brave/brave-search-mcp-server
Required — set BRAVE_API_KEY in the env section below (treat as a secret).
Docs: https://github.com/brave/brave-search-mcp-server
Workflow combinations¶
Five remote search services and one community stdio entry. They're substitutable but each has a different latency / quality / quota profile, so the meaningful "combination" is choosing one as primary and one as fallback:
- Primary + fallback —
Tavily(LLM-tuned answers) primary,Exa(semantic search) fallback. Tavily fails fast on quota; Exa picks up. - Crawl + index —
Firecrawl(crawls + structured extract) feeding a downstream Vector Database run. Good when the agent needs the content of pages, not just the URLs. - Search-engine results —
SerpAPIwhen you specifically want Google / Bing SERP JSON without scraping. - Long-form context retrieval —
Jina AIfor embedding + reader API; the model gets cleaned-up article bodies, not raw HTML. - Privacy-first local-stdio —
Brave Search(stdio) when you don't want a remote OAuth dance and you have a Brave API key.
Auth & secrets¶
All six entries are API-key gated. Set the key as a ${VAR} placeholder in the form (header for remote, env for stdio):
| Connection | Auth | Env / header |
|---|---|---|
| Tavily | API key | Authorization: Bearer ${TAVILY_API_KEY} |
| Exa | API key | x-api-key: ${EXA_API_KEY} |
| Firecrawl | Bearer | Authorization: Bearer ${FIRECRAWL_API_KEY} |
| Jina AI | Bearer | Authorization: Bearer ${JINA_API_KEY} |
| SerpAPI | API key (query param style; configurable as ${SERPAPI_KEY}) |
per-vendor docs |
| Brave Search (stdio) | API key | env.BRAVE_API_KEY = ${BRAVE_API_KEY} |
Every remote vendor on this page ships a free tier large enough for tutorial-scale agent use — the free quotas are intended for evaluation, not production, but a single agent session won't exhaust them.
Picking guide¶
| If you need… | Reach for |
|---|---|
| LLM-shaped answers with citations | Tavily |
| Neural / semantic search | Exa |
| Crawl + structured extract | Firecrawl |
| Embedding-friendly reader API | Jina AI |
| Raw SERP JSON | SerpAPI |
| Privacy-first, local-process search | Brave Search (stdio) |