Context7
Up-to-date docs for AI agents
제작자가 쓴 설명(영어 원문)
Web malware techniques, kits and EtherHiding contracts from Ohey's website scans. No sign-in.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://ohey.ca/mcp/research터미널에서 이 명령어를 실행하세요
claude mcp add --transport http research https://ohey.ca/mcp/research프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"research": {
"url": "https://ohey.ca/mcp/research"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"research": {
"type": "http",
"url": "https://ohey.ca/mcp/research"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://ohey.ca/mcp/research메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
도구 이름과 설명은 서버가 2026년 11월 6일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.
list_threatsEvery technique Ohey publishes, with its page, a summary, site counts and the slugs of its kits. get_threat on a technique lists its kits with names and site counts in one call.
get_threatA technique or kit page's statistics: sites matched by month, how many sites were still infected when rescanned, WordPress and Joomla shares, common plugins and core versions, kits seen together on the same sites, its EtherHiding contracts, the hosts its ClickFix commands fetch f
list_research_articlesOhey research articles, newest first: incident write-ups with timelines, code analysis and indicators. get_article returns one article's facts and indicators.
get_articleOne research article's summary, key facts (sample hashes, active window, scale) and its indicators of compromise section as Markdown, defanged as published. Read the page at url for the full write-up.
search_etherhiding_contractsSmart contracts that compromised websites read their next stage from, as the EtherHiding contract tracker lists them: chain, kit, current destinations and when Ohey last read each one. firstSeen is the day Ohey first read the contract, not when it was deployed; many contracts sha
get_etherhiding_contractOne contract's destinations over time, the contracts or endpoints it names next, and when Ohey first and last read it. Returns contracts as an array, one entry per chain the address is tracked on (usually one), each with history: its 20 most recent changes, and historyCapped is t
get_feed_statsThe size of the Ohey feed and the last seven full UTC days of changes to it, ending the day before asOf. hosts: hosts in the feed now. denied: hosts confirmed as legitimate services and kept out. week.added (and daily): hosts that entered the feed. week.entered: website tips that
search_clickfix_commandsHosts that ClickFix lure commands fetch from or report to, as the ClickFix command tracker lists them, busiest first or newest first: the kits credited with each (a ClickFix kit is credited when it is on at least half the sites whose command used the host), sites whose captured c
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 도메인 ohey.ca 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
590ms 만에 응답(HTTP 200)
로그인 필요 없음
도구 설명 8개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.0.0)은 그저께 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: Context7, Codebase Memory, Exa
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Ohey scans websites for injected malware: ClickFix and fake update lures, skimmers, phishing kits, EtherHiding loaders, and the C2 and distribution servers behind them. There are two remote MCP servers (Streamable HTTP).
| Server | URL | Sign-in |
|---|---|---|
| Research | https://ohey.ca/mcp/research | None |
| Feed and API | https://ohey.ca/mcp | Ohey account with API access |
Both servers are remote Streamable HTTP servers, so there is nothing to download. The examples add the research server; for the feed server, use the name ohey and the URL https://ohey.ca/mcp, and the client opens ohey.ca to sign in the first time.
Both are in the MCP Registry as ca.ohey/research and ca.ohey/ohey.
Web, desktop and mobile: Settings, Connectors, Add custom connector, then paste the URL.
Claude Code:
claude mcp add --transport http ohey-research https://ohey.ca/mcp/research
Custom MCP servers need developer mode, which OpenAI offers on some plans and has moved between settings pages; a Business or Enterprise admin may have to allow custom connectors first.
codex mcp add ohey-research --url https://ohey.ca/mcp/research
For the feed server, add it with --url https://ohey.ca/mcp, then run codex mcp login ohey to sign in. Or in ~/.codex/config.toml:
[mcp_servers.ohey-research]
url = "https://ohey.ca/mcp/research"
gemini mcp add --transport http ohey-research https://ohey.ca/mcp/research
Or in settings.json, under mcpServers:
"ohey-research": { "httpUrl": "https://ohey.ca/mcp/research" }
For the feed server, run /mcp auth ohey in the CLI to sign in.
In ~/.cursor/mcp.json, or .cursor/mcp.json in a project:
{
"mcpServers": { "ohey-research": { "url": "https://ohey.ca/mcp/research" } } }
code --add-mcp '{"name":"ohey-research","type":"http","url":"https://ohey.ca/mcp/research"}'
Or run MCP: Add Server, choose HTTP and paste the URL. The JSON form, in .vscode/mcp.json or your user mcp.json:
{
"servers": { "ohey-research": { "type": "http", "url": "https://ohey.ca/mcp/research" } } }
Any client that supports remote MCP servers over Streamable HTTP takes the URL as is. Most read an mcpServers object with a url (some call the field serverUrl or httpUrl). A client that only runs local stdio servers can reach either one through mcp-remote:
{
"mcpServers": { "ohey-research": { "command": "npx", "args": ["-y", "mcp-remote", "https://ohey.ca/mcp/research"] } } }
The research Ohey publishes on ohey.ca/threats and ohey.ca/research, as tools. Anyone can connect, with no sign-in.
| Tool | What it does |
|---|---|
list_threats | Every technique, with its page, a summary, site counts and its kits. |
get_threat | A technique or kit: sites matched by month, how many were still infected when rescanned, WordPress and Joomla shares, common plugins, kits seen on the same sites, its EtherHiding contracts, its ClickFix command hosts and articles. |
list_research_articles | Research articles, newest first. |
get_article | One article's summary, key facts (hashes, active window, scale) and its indicators of compromise, as Markdown. |
search_clickfix_commands | Hosts that ClickFix lure commands fetch from, by kit or host, with the latest command for each, defanged. |
search_etherhiding_contracts | Contracts that compromised sites read their next stage from, by kit, chain or destination host. |
get_etherhiding_contract | One contract's destinations over time. |
get_feed_stats | Feed size, last week's additions and removals, and the capture archive. |
Counts update daily from Ohey's scans. Both search tools take offset to page past limit, and sort: "firstSeen" for the newest first. A host search that finds nothing returns a coverage note: the trackers list only contract destinations and command hosts, so a miss means "not tracked", not "clean". Checking any host against the full feed is the feed server's job.
Hosts and commands are live malware infrastructure. They come defanged ([.], hxxp), and results that carry commands include a notice for the person reading. Refang or run them only in an isolated research environment. See the terms.
Ohey's API as tools: look up any host, search the feed, read CVEs and scan URLs. You sign in with your Ohey account, so there is no API key to copy. Ask for an account with API access at ohey.ca/contact.
Connect it the same way as the research server, with https://ohey.ca/mcp as the URL (Install). Signing in opens ohey.ca; approve the connection there and the client gets access. Clients register themselves from the server's OAuth metadata, so there is no client ID to set.
| Tool | What it does |
|---|---|
search_indicators | Hosts in the feed, filtered by tag or family, with roles, families, tags and the reason each was admitted. |
get_host | A host's feed entry, vulnerable software from its latest capture, its captures summary and DNS records. |
get_host_captures | Each time the scanner loaded the host: when, what it returned and what matched. |
list_delisted | Hosts that review excluded or took out of the feed, with the reason and who decided. |
get_vulnerability | One CVE with its NVD, EPSS, KEV, GitHub and OSV data. |
list_vulnerabilities | Published CVEs in order, or only WordPress plugin, theme and core CVEs. |
start_scan | Loads a URL in Ohey's scanner and records what it finds. |
get_scan | The scan result: whether the page is malicious, what matched, commands and clipboard writes it tried to plant, and suspected C2. |
The scan tools appear only when you tick "Scan URLs" while approving. Scans count against your account.
Approving a client creates an API key named after it, under Account in the Ohey portal. Tool calls are rate limited and counted against that key like any API request. Revoke the key to disconnect the client.
The full API, with every response field, is documented at ohey.ca/docs.
Report security issues to hey@ohey.ca. See security.txt.