Research MCP

io.github.research-mcp-hq由 GitHub 账号 research-mcp-hq 发布v0.1.2更新于 Oct 24, 2026

Cited research MCP (MCP+agent infra): brief, lookup. Fail=$0.

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆

概览

AI 生成的概览

付费远程 MCP 服务器,让助手获得带引用的研究简报和单一来源核查,聚焦 AI 基础设施、MCP 与安全主题。

可以做什么
围绕 AI 基础设施、MCP 与安全主题生成带引用、与查询绑定的摘录包,可选快速或标准深度,返回摘要、正文、置信度、来源、缺口和截止日期。抓取并核验单个 URL 或论断,返回同样的结果结构并附上论断与摘录。当引文无法在来源 URL 上通过核验时拒绝该次运行,且不计费。通过计费额度接口查询预付余额和公开价目表。
适用场景
当助手需要关于 AI 基础设施、MCP 或安全的可引用、有出处的调研,或需要核验单个 URL 或论断,且用户愿意按成功调用从预付余额中付费时使用。
运行要求
远程 streamable HTTP 端点,无需本地安装。需要预付结账获得的 bearer API 密钥,放在 Authorization 请求头中(也接受 X-API-Key 请求头)。需要能访问托管端点的网络。额度须预先购买。
安装前请注意
付费服务:预付包为 10、25 或 50 美元,计费成功按 lite 调用 0.25 美元、标准简报 0.60 美元计费;失败或被拒绝的运行不计费。API 密钥属于机密,应避免写入共享配置。README 称仅记录类别层面的使用情况而非提问内容,且需求日志为选择性开启、默认关闭。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Research MCP,将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储,绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.research-mcp-hq%2Fresearch-mcp/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "research": {
      "type": "http",
      "url": "https://mcp.researchmcp.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

research-mcp

Paid cited research remote MCP for coding / research agents (API key auth, not OAuth).

Why pay: query-tied excerpt packs from allowlisted primaries; refuse uncited — that call is $0. Prepaid packs; meters only on billable successes.

Repo may be private; treat this README as the agent-facing contract. Live Fly host is unchanged.

Marketing site (Cloudflare Pages)

Source of truth: research-mcp-hq/www (public/). Live site: https://researchmcp.dev.

The www/ tree in this repo is a stub / mirror note only — do not point Cloudflare Pages here. MCP API origin remains on Fly; branded install URL is https://mcp.researchmcp.dev/mcp.

MCP URL (production)

https://mcp.researchmcp.dev/mcp

Health: https://mcp.researchmcp.dev/health
Server card: https://mcp.researchmcp.dev/.well-known/mcp/server-card.json
Credits meter: GET https://mcp.researchmcp.dev/billing/credits (auth’d)

json
{  "mcpServers": {    "research-mcp": {      "url": "https://mcp.researchmcp.dev/mcp",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

Auth

Every /mcp and /billing/credits request:

  • Authorization: Bearer <key> or
  • X-API-Key: <key>

Keys: prepaid customer key (from Checkout success page) or break-glass API_KEYS (ops; no ledger debit).

Privacy (demand signals)

We log category mix (tool, topic bucket, host, billable vs fail=$0) — not your questions. Opt-in via DEMAND_LOG=1 on the server; default off.

Pricing (locked)

PackCredits
$10 starter1000¢
$25 standard2500¢
$50 pro5000¢
Meter (billable success)Price
lite (source_lookup, research_brief depth=quick)$0.25
standard (research_brief depth=standard)$0.60
deep (preview only)$1.50 published meter; preview path always $0

fail = $0: sample/demo, quote-gate fail, density fail, COGS abort, cancel, depth-mismatched golden, preview/parked paths (meta.billable=false, charge_usd=0).

Inspect balance + tables: GET /billing/credits → balance_cents, packs, meters_usd, fail_usd: 0. Break-glass returns { break_glass: true, balance_cents: null } (no fake balance).

When to call each tool

Live (default paid surface)

ToolCall whenDo not
research_briefYou need cited, query-tied excerpt packs on AI infra / MCP / security. depth=quick ($0.25) or depth=standard ($0.60).Do not use depth=deep (parked / sample only unless preview flag).
source_lookupYou have one URL or claim to fetch/verify. Lite $0.25.Do not use as open-web search or multi-source synthesis.

Both return the shared envelope: tldr, body, confidence, sources, gaps, as_of, plus schema_version (2026-09-14). Optional fail_gate: { reason, retryable }, claims / excerpts, retrieved_at. If quotes fail verification on source_url, the run is refused and not billed.

Preview / parked (ENABLE_PREVIEW_TOOLS=1)

Tool / pathBehavior
compare_optionsRegistered only with the flag. Always $0 / billable=false. No live path — prefer research_brief.
depth=deepAllowed only with the flag. Always $0. Soft-reserve never demands full deep SKU.

Without the flag: compare_options is not registered; depth=deep is rejected (preview_required). Directory card still says do-not-call for compare/deep.

No stub billing. No 25-tool kitchen sink — two live tools by default.

Published contract

Quickstart (local)

bash
cd /workspace/research-mcpnpm install && npm run buildAPI_KEYS=dev-key-1 npm start# optional live brief path:LIVE_RESEARCH=1 API_KEYS=dev-key-1 npm start
bash
curl -s http://127.0.0.1:3000/healthcurl -s -X POST http://127.0.0.1:3000/mcp \  -H 'Content-Type: application/json' \  -H 'Accept: application/json, text/event-stream' \  -H 'Authorization: Bearer dev-key-1' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Env (high-signal)

VarNotes
API_KEYSBreak-glass keys (comma-separated)
LIVE_RESEARCH=1Live search→extract→synthesize→quote gate for quick/standard
ENABLE_PREVIEW_TOOLS=1Register compare + allow deep (always $0)
DATABASE_URLSQLite ledger for customer keys / credits
Stripe STRIPE_* / pack price IDsPrepaid Checkout (test until go-live)

Tests

bash
npm run eval:all      # goldens + off-golden + pipelinenpm run test:billing  # ledger / webhook / credits meter

Layout

  • src/server.ts — tool registration (finish-or-hide)
  • src/billing/credits.ts — GET /billing/credits (T10 visible meter)
  • src/contract.ts — schema_version + fail_gate
  • docs/contract/ — published JSON Schema + examples
  • ARCHITECTURE.md — transport / auth / metering

Discovery

Homepage for listings: https://researchmcp.dev, not Smithery.

Ops

See RUNBOOK.md. License: MIT.

来源:README.md,提交 15ce435

工具

0
该服务器需要 API 密钥等凭据,因此 SourceWeft 无法在没有凭据的情况下读取其工具,也未收录。

版本历史

1
  1. v0.1.2最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分