Hyperresearch Answers

หนึ่งคำถาม หนึ่งคำตอบที่ตรวจสอบแล้วสำหรับ AI agents ask จะคืนคำตอบสั้น ๆ ที่ตรวจสอบคำต่อคำกับแหล่งอ้างอิงที่อ้างถึง หรือคืนค่า not-found อย่างตรงไปตรงมา search จะคืนแหล่งข้อมูลดิบที่จัดอันดับพร้อมข้อความตรงจากเว็บและแหล่งข้อมูลแบบมีโครงสร้างประมาณ 45 แหล่ง (เอกสารยื่นต่อหน่วยงาน, สถิติ, ทะเบียน, งานวิชาการ, หนังสือ) ระยะไกล ใช้ OAuth 2.1 หรือ API key คิดค่าบริการต่อการเรียกเริ่มต้นที่ 5 เซนต์ เครดิตฟรี $5 ไม่ต้องใช้บัตร

เซิร์ฟเวอร์ MCP แบบโฮสต์

npx add-mcp 'https://answers.hyperresearch.ai/mcp'

ติดตั้งลง Claude Code, Codex, Cursor และอื่นๆ

เอกสาร

Answers MCP: ask one question, get one checked answer

Answers MCP gives an AI agent the ask tool at https://answers.hyperresearch.ai/mcp. The agent sends one question and gets back a short answer with the quotes it rests on, each checked against its page. The research happens on our side: no search loop in the agent, no pages flooding its context, no context rot. Every account gets $5 of free credit, no card needed.

ask

One call instead of thirty searches. ask searches the open web and about 45 structured sources, checks each quote against the page it came from, and checks the answer against the quotes. If nothing supports an answer, you get not_found instead of a guess.

Modes: fast 5¢, standard 10¢ (20¢ if it digs deeper), max 50¢.

{
  "question": "How old must a US senator be?",
  "mode": "fast"
}

Result, shortened:

{
  "status": "answered",
  "answer": "At least 30 years old (US Constitution, Article I, Section 3).",
  "evidence": [
    {
      "url": "https://www.archives.gov/founding-docs/constitution-transcript",
      "quote": "No Person shall be a Senator who shall not have attained to the Age of thirty Years",
      "check": "verified"
    }
  ],
  "price_cents": 5
}

Need raw sources? search

When your agent wants to read the sources itself, search returns them ranked, each with the passages that matched, copied word for word. No summary, no rewriting. standard is 5¢ a call; max is 15¢: every provider, plus structured data and tables from PDFs, for hard lookups.

{
  "query": "minimum age to serve as a US senator",
  "max_results": 10
}

Result, shortened:

{
  "results": [
    {
      "rank": 1,
      "url": "https://www.archives.gov/founding-docs/constitution-transcript",
      "title": "The Constitution of the United States: A Transcription",
      "kind": "web",
      "passages": [
        { "text": "No Person shall be a Senator who shall not have attained to the Age of thirty Years", "verified": true }
      ]
    },
    { "rank": 2, "url": "https://constitution.congress.gov/browse/article-1/section-3/", … }
  ],
  "price_cents": 5
}

The open web, then the records behind it

Every search and every ask also queries the structured sources that fit the question. One call, with no source to pick and no extra key to hold.

  • Company filings and registers. SEC EDGAR, Companies House, EDINET, HKEX, CNINFO, GLEIF
  • Statistics agencies. FRED, Eurostat, e-Stat, World Bank, OECD, IMF, US Treasury Fiscal Data
  • Scholarly indexes. OpenAlex, PubMed, Europe PMC, arXiv, bioRxiv, ClinicalTrials.gov
  • Books. Open Library, Google Books, HathiTrust, Internet Archive
  • Government records. Federal Register, eCFR, GovInfo, Congress.gov, Regulations.gov, USAspending, Grants.gov, openFDA, NPI Registry
  • Research funding. NIH RePORTER, NSF Awards, CORDIS, UKRI Gateway to Research
  • Code, forums and reference. GitHub, Hacker News, Stack Exchange, X, Wikipedia

The sources a Hyperresearch research run reads: https://hyperresearch.ai/sources

Quotes and an honest not found

  • Word-for-word quotes. Every passage is matched against the page it came from. One that does not match is marked unverified.
  • An honest not found. When no source supports an answer, ask says so. A not-found answer costs 20% to 100% of the call.
  • Citable by default. Each answer carries the URL and the exact quote.
{
  "status": "not_found",
  "answer": "No source we could read states this figure.",
  "evidence": [],
  "price_cents": 2
}

Pricing

CallWhat it doesPriceIf not found
ask · fastA quick lookup. Returns not found rather than digging further.5¢1¢–5¢
ask · standardDigs further on its own when the first pass comes back thin (20¢ when it does).10¢2¢–20¢
ask · maxThe longest search. Numbers must agree across two sites.50¢10¢–50¢
search · standardRanked sources with word-for-word passages.5¢0¢–5¢
search · maxEvery provider, plus structured data and tables from PDFs. For hard lookups.15¢0¢–15¢
  • Every account gets $5 of free credit, once. No card needed.
  • Top-ups start at $10.
  • Auto-reload is optional and stays off until you switch it on.
  • A call that fails on our side costs nothing.

Benchmarks

Results coming soon.

Method:

  • Harness: the open-source Artificial Analysis Search Index harness (Stirrup), run by us.
  • One fixed agent model, the same for every provider, with up to 25 turns per question.
  • 30 questions: 10 each from AA-Omniscience (public), DeepSearchQA, BrowseComp.
  • The same questions for every search provider; only the search tool changes.

Connect

The server: https://answers.hyperresearch.ai/mcp

Paste this into your coding agent. It adds the server and you sign in on first use:

Fetch and execute the appropriate instructions to set me up for Hyperresearch Answers from https://hyperresearch.ai/answers/setup/prompt.md

The prompt: https://hyperresearch.ai/answers/setup/prompt.md

Or add it directly:

  • Add to Claude. Also works in Claude Desktop, and in Claude Code when you are logged in with a claude.ai account.
  • Add to Cursor (or the app link cursor://anysphere.cursor-deeplink/mcp/install?name=hyperresearch-answers&config=eyJ1cmwiOiJodHRwczovL2Fuc3dlcnMuaHlwZXJyZXNlYXJjaC5haS9tY3AifQ%3D%3D)
  • Add to VS Code

On first use, a browser window opens: sign in to Hyperresearch and approve. No API key needed.

Claude Code

claude mcp add --transport http -s user hyperresearch-answers https://answers.hyperresearch.ai/mcp

Then run /mcp in a session and sign in. With an API key (answers:ask scope), for CI:

claude mcp add --transport http -s user hyperresearch-answers https://answers.hyperresearch.ai/mcp \
  --header "Authorization: Bearer $HYPERRESEARCH_API_KEY"

VS Code from a terminal

code --add-mcp '{"name":"hyperresearch-answers","type":"http","url":"https://answers.hyperresearch.ai/mcp"}'

ChatGPT

Open ChatGPT Plugins (https://chatgpt.com/plugins), select the plus button, then Add custom MCP server. Enter https://answers.hyperresearch.ai/mcp as the URL, choose OAuth, select Create as a plugin and sign in. OpenAI offers custom MCP servers on ChatGPT Business, Enterprise and Edu, on the web; on Business, only workspace admins and owners can add one.

Other clients

npx add-mcp https://answers.hyperresearch.ai/mcp

JSON config, most clients (browser sign-in on first connect):

{
  "mcpServers": {
    "hyperresearch-answers": {
      "url": "https://answers.hyperresearch.ai/mcp"
    }
  }
}

With an API key (create one with the answers:ask scope at https://console.hyperresearch.ai/#/keys):

{
  "mcpServers": {
    "hyperresearch-answers": {
      "url": "https://answers.hyperresearch.ai/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

Windsurf reads serverUrl instead of url:

{
  "mcpServers": {
    "hyperresearch-answers": {
      "serverUrl": "https://answers.hyperresearch.ai/mcp"
    }
  }
}

Answers and Deep

Answers MCP is for the lookups an agent makes many times a task. When the question needs a full report with every citation checked, a Deep research run researches it end to end: https://hyperresearch.ai/pricing

Create an account: https://console.hyperresearch.ai/login