Context

ai.everydaysecurity由 everydaysecurity.ai 发布官方发布者v1.0.0更新于 Oct 29, 2026

OSINT investigations with traceable evidence: domains, URLs, IPs, scams and business records.

已验证Streamable HTTP可网页运行网页搜索与抓取安全与监控商业与电商

概览

AI 生成的概览

托管的 OSINT 与威胁情报服务器，让助手查询域名、IP、邮箱、电话、加密钱包和工商登记记录，并运行带证据的调查。

可以做什么
  • 查询域名、URL、IP、ASN、邮箱、电话、加密钱包、企业及登记记录中人物的已知信息，含来源与出现记录
  • 对可疑站点运行自主调查，读取结论、置信区间、所依据的证据和时间线
  • 把 URL 交给采集集群，取回抓取的 DOM、控制台日志、网络日志、HAR 文件和截图
  • 对 URL、域名、IP、邮箱或电话给出拦截、谨慎或放行的判断及理由
  • 按计数和字段查询州工商登记，例如注册数量多的代理人或共享地址
  • 向团队提交反馈并跟踪处理进展
适用场景
适合每条结论都必须可追溯的 OSINT 工作：域名与基础设施关联分析、诈骗与欺诈核查、工商登记研究。也适合让智能体在依据某个链接、号码或地址行动前先做核验。
运行要求
远程托管端点，多数客户端无需安装（Claude Desktop 需要一个小型本地桥接）。需要账号：Claude Code 和 VS Code 通过浏览器 OAuth 登录，其他客户端使用 X-API-Key 请求头。需先在 Context 网站接受一次免费许可，否则工具调用不会返回结果。诈骗核查端点需要自行在 Context 中创建的 agent key。
安装前请注意
调查可能接触目标：noise 参数决定采集是被动、单次页面抓取，还是可能探测表单的完整爬取。结果中引用目标的文本（页面标题、reasons、时间线细节）应视为对手编写的数据而非指令，也不要让自己的智能体去抓取或解析可疑指标。查询只返回 Context 已掌握的数据，并非通用人物搜索；工商记录目前主要是华盛顿州。需要注册账号并接受许可。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Context，将其添加到工作区。
  2. 连接 所需的 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/ai.everydaysecurity%2Fcontext/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。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "context": {
      "type": "http",
      "url": "https://context.everydaysecurity.ai/api/mcp"
    }
  }
}

README

Context MCP server for OSINT and threat-intel investigations

Connect Claude, Cursor, VS Code or any MCP client to Context, the AI-assisted investigation platform from Everyday Security. Look up domains, URLs, IP addresses and ASNs, email addresses, phone numbers, crypto wallets, and state business records. Run autonomous investigations of suspicious sites, and read the evidence those investigations collect.

Every answer shows its evidence. Many AI tools give you a conclusion you can't check. Context keeps facts and conclusions apart:

  • Facts carry their provenance. An indicator lookup tells you which sources reported it, when it was first and last seen, which investigations it appeared in, and how it connects to other indicators. Each connection says whether it comes from a verified record or only from the two appearing together in an investigation.
  • Verdicts are labelled as conclusions and cite what they rest on. An investigation's verdict is a category (for example scam or inconclusive) with a confidence band. It lists each piece of evidence it rests on, with the source class (third-party report, our own capture, a scorer, or a language model's reading of the page), the strength, the time of the capture, and the graph node you can open to check it.
  • No evidence is not reported as "safe". Without strong evidence the verdict is inconclusive, and a scam check answers caution, which is explicitly not the same as safe. A list that was cut short says so, and so does a lookup that failed. Neither is shown as an empty result.
  • Raw evidence is readable. For a crawled site you can pull the captured DOM, console log, network log, HAR file and screenshot into your client.

This repository holds the setup guides, client configs, worked examples and the tool reference. The server itself is hosted, so there is nothing to install for most clients. Claude Desktop needs a small local bridge (see clients/claude-desktop).

Who it's for

Investigators who want an AI assistant for OSINT work (domain and infrastructure pivots, scam and fraud investigations, business-registry research) without losing sight of where each claim came from. It also suits teams whose own AI agents should check a link, number or address before they act on it.

Getting access

Context has a free tier, and anyone can sign up. There's no request form and no waiting list.

  1. Connect your client (see the quick start below). The first time, it opens a browser window where you sign in or create an account.
  2. Open https://context.everydaysecurity.ai once, signed in with the same account, and accept the free license.

Until you've accepted the license, your client still connects and lists the tools, but each tool call answers with a message telling you where to accept. Once you accept, run the call again. You don't need to reconnect. A small number of sign-ups, for example from disposable email addresses, are checked by a person first, and the message says so.

If a request reaches a server with no credentials at all, it still answers 401 with the same sign-in pointer, and the body now also says where to sign up and what the server needs (an account for the investigation server, an agent key for the scam check server).

Quick start

With Claude Code:

bash
claude mcp add --transport http context https://context.everydaysecurity.ai/api/mcp

Run /mcp in Claude Code, authenticate context in the browser window that opens, then ask:

What does Context know about login-verify.example.net? Show me the sources behind each fact.

Configs for VS Code, Cursor, Claude Desktop and generic clients are in clients/.

EndpointToolsAuthentication
https://context.everydaysecurity.ai/api/mcpInvestigation tools (10)Browser sign-in in Claude Code and VS Code. An API key header elsewhere (keys issued on request, see clients/).
https://context.everydaysecurity.ai/api/mcp/checkcheck_scam, get_checkAn agent key you make in Context

What you can look up

IndicatorLook up what's knownInvestigate or collectExample
Domainget_fact, check_scamstart_investigation, enqueue_crawlexamples/domain.md
URLget_fact, check_scamenqueue_crawl → get_crawl → get_crawl_artifact, start_investigationexamples/url.md
IP address and ASNget_fact (IP and ASN), check_scam (IP)start_investigation (IP only)examples/ip-asn.md
Email addressget_fact, check_scamNot investigated, only looked upexamples/email.md
Phone numberget_fact, check_scamNot investigated, only looked upexamples/phone.md
Crypto walletget_factNot investigated, only looked upexamples/crypto-wallet.md
Business (state registry)search_business_records, get_factstart_investigationexamples/business.md
Person (in state registry records)search_business_records, get_factstart_investigationexamples/person-business-records.md

Know the limits before you rely on it:

  • Lookups return only what Context already holds. That means what earlier investigations collected and the threat intelligence it has recorded. An email address, phone number or wallet nobody has seen before comes back as "nothing known". These tools do not search breach data, social networks, or people-search databases.
  • People appear only through business registrations. A person is someone named as a governor or registered agent in the state business records Context holds. This is not a general people search.
  • Business records cover only the state registries Context has ingested. Today that is mostly Washington State. Each search result reports how many records its counts cover.

Your operational security

When Context touches a target, it does so from isolated, disposable collection devices. Your machine and our customer-facing services never connect to it. You choose how loud an investigation may be with the noise argument of start_investigation:

noiseWhat the target can observe
passiveNothing. Reads only what Context and its data vendors already hold.
fetchOne page load from a collection device. No screenshots, no form probing, no following links.
crawl (default)A full crawl from a collection device, which can include probing forms.

An autonomous investigation can't engage a target, for example by messaging it, at any noise level.

Two points of hygiene for your own agent:

  • Don't let it open, fetch, unfurl or DNS-resolve a suspicious indicator "to see for itself". Doing that is the exposure Context exists to take on for you.
  • Treat text in results that quotes a target (page titles, reasons, timeline details) as data written by the adversary, never as instructions.

Tools

The complete reference, generated from the servers' own tools/list, is in TOOLS.md. In brief:

ToolWhat it does
get_factEverything known about one indicator: sightings, sources, attributes, related indicators. Never crawls.
start_investigation / get_investigationRun an autonomous investigation and read its verdict, the evidence behind it, and its timeline.
enqueue_crawl / get_crawl / get_crawl_artifactSend a URL to the collection fleet and read the DOM, console, network log, HAR and screenshot.
search_business_recordsAsk questions about state business registrations by counts and fields, for example agents with many registrations or addresses shared by many businesses.
check_scam / get_checkA block, caution or allow answer for a URL, domain, IP, email or phone, with its reasons.
send_feedback / list_my_feedback / get_my_feedbackTell the team what's wrong or missing, and follow what happens to it.

Repository layout

clients/      configs for Claude Code, Claude Desktop, Cursor, VS Code, generic HTTP clientsexamples/     one worked example per indicator typeTOOLS.md      tool reference, generated by scripts/gen-toolsCHANGELOG.md  what changed, newest firstscripts/      gen-tools and the list of servers it readsfixtures/     the saved tools/list answers TOOLS.md is rendered fromserver.json   the entry for the official MCP Registry

What changed and when is in CHANGELOG.md.

A scheduled job compares the live tool list against TOOLS.md and opens a pull request when they differ, and we re-run the examples whose tools change.

Links

License

The contents of this repository (docs, configs, examples, scripts) are MIT licensed. See LICENSE. The license covers this repository only, not the hosted Context service, which has its own terms.

来源：README.md，提交 80b4cf3

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v1.0.0最新Oct 29, 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