a9n9 Deep Research
Objective-driven deep research: free daily quick search plus MPP-paid cross-source browser reports.
Connect it
Settings → Connectors → Add custom connector
URL: https://agent.a9n9.net/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://agent.a9n9.net/mcp{
"mcpServers": {
"deep-research": {
"url": "https://agent.a9n9.net/mcp"
}
}
}claude mcp add --transport http deep-research https://agent.a9n9.net/mcp{
"servers": {
"deep-research": {
"type": "http",
"url": "https://agent.a9n9.net/mcp"
}
}
}5 tools, verified live
a9n9_quick_searchread-onlyFree first-level search, limited per day across all callers: current news coverage (100+ languages, 250K+ sources) or scholarly papers (arXiv). Returns structured results immediately with no payment. When the daily quota is exhausted, or when you need live browsing and synthesis across sources, use a9n9_research_quote for paid deep research.
a9n9_research_quoteread-onlyAnalyze a deep-research objective and return the exact current price, limits, planned start URLs, request hash, expiry, payment requirements, and cloud-browser capabilities without charging or starting a job. targetUrl is optional: omit it and the quote derives and binds a bounded plan of public start URLs from the objective.
a9n9_research_startStart bounded paid research in a real remotely hosted Browserbase Chromium session with JavaScript rendering, DOM interaction, scrolling, and dynamic-content extraction, followed by gpt-5.6-luna synthesis. targetUrl is optional; without it the quoted plan of public start URLs derived from the objective is executed. Call a9n9_research_quote first when price visibility is needed. The service does no
a9n9_research_submit_paymentVerify a separately broadcast Tempo mainnet push-mode payment and continue the quoted research job. Use the paymentChallenge and walletPayment returned by a9n9_research_quote, then provide the transaction hash, payer address, and same job_key.
a9n9_research_statusread-onlyReturn milestone progress and the final result for an opaque tracker code.
Alternatives in Browser & Scraping
Compare →WAWavedashB
Wavedash docs and workflow guidance for building and publishing browser games.
WSWeb Scraping MCP ServerB
Generic URL crawl + HTML extraction — fallback for sites without dedicated MCPs.
SWSeo Web Analysis MCP ServerB
Site crawl + tech stack + DNS + SSL + WHOIS — five web-intel layers in one MCP.
PMPlaywright MCP ServerB
Headless browser primitives for AI agents when sites need real JS rendering.
URLpipeB
Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.
IAImgVX AIB
Find the free ImgVX AI browser tool for any image job: remove backgrounds, upscale, compress.