StackScan Tech Lookup API를 사용하여 웹사이트의 기술 스택을 식별하고 상세한 기업 정보를 조회합니다.
다른 이름 stackscan/stackscan-mcp, stackscan-mcp, @stackscan/mcp-server
- 스타
- 3
- Tools
- 6
- 다운로드, 30일
- —
- 최신 버전
- 0.4.0
- 마지막 커밋
- 2026년 10월 2일
- 라이선스
- MIT
StackScan MCP란?
StackScan은(는) MCP server입니다. StackScan Tech Lookup API를 사용하여 웹사이트의 기술 스택을 식별하고 상세한 기업 정보를 조회합니다. 6개 도구를 제공합니다. 예: check_credits, lookup_company, lookup_domain_technologies.
프로젝트 README에서 생성된 요약
StackScan MCP 설치 방법
형식 확인: 2026년 11월 10일Cursor에 추가Goose에 추가Claude Code에 StackScan MCP 설치
$ claude mcp add --env 'STACKSCAN_API_TOKEN=<YOUR_STACKSCAN_API_TOKEN>' --env 'STACKSCAN_TENANT_ID=<STACKSCAN_TENANT_ID>' stackscan-mcp -- npx -y @stackscan/mcp-serverCursor에 StackScan MCP 설치
~/.cursor/mcp.json
{
"mcpServers": {
"stackscan-mcp": {
"command": "npx",
"args": [
"-y",
"@stackscan/mcp-server"
],
"env": {
"STACKSCAN_API_TOKEN": "<YOUR_STACKSCAN_API_TOKEN>",
"STACKSCAN_TENANT_ID": "<STACKSCAN_TENANT_ID>"
}
}
}
}VS Code에 StackScan MCP 설치
.vscode/mcp.json
{
"servers": {
"stackscan-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@stackscan/mcp-server"
],
"env": {
"STACKSCAN_API_TOKEN": "<YOUR_STACKSCAN_API_TOKEN>",
"STACKSCAN_TENANT_ID": "<STACKSCAN_TENANT_ID>"
}
}
}
}VS Code CLI에 StackScan MCP 설치
$ code --add-mcp '{"name":"stackscan-mcp","type":"stdio","command":"npx","args":["-y","@stackscan/mcp-server"],"env":{"STACKSCAN_API_TOKEN":"<YOUR_STACKSCAN_API_TOKEN>","STACKSCAN_TENANT_ID":"<STACKSCAN_TENANT_ID>"}}'Claude Desktop에 StackScan MCP 설치
claude_desktop_config.json
{
"mcpServers": {
"stackscan-mcp": {
"command": "npx",
"args": [
"-y",
"@stackscan/mcp-server"
],
"env": {
"STACKSCAN_API_TOKEN": "<YOUR_STACKSCAN_API_TOKEN>",
"STACKSCAN_TENANT_ID": "<STACKSCAN_TENANT_ID>"
}
}
}
}Codex에 StackScan MCP 설치
$ codex mcp add stackscan-mcp --env 'STACKSCAN_API_TOKEN=<YOUR_STACKSCAN_API_TOKEN>' --env 'STACKSCAN_TENANT_ID=<STACKSCAN_TENANT_ID>' -- npx -y @stackscan/mcp-serverCodex config.toml에 StackScan MCP 설치
~/.codex/config.toml
[mcp_servers.stackscan-mcp] command = "npx" args = ["-y", "@stackscan/mcp-server"] [mcp_servers.stackscan-mcp.env] STACKSCAN_API_TOKEN = "<YOUR_STACKSCAN_API_TOKEN>" STACKSCAN_TENANT_ID = "<STACKSCAN_TENANT_ID>"
Gemini CLI에 StackScan MCP 설치
$ gemini mcp add -s user -e 'STACKSCAN_API_TOKEN=<YOUR_STACKSCAN_API_TOKEN>' -e 'STACKSCAN_TENANT_ID=<STACKSCAN_TENANT_ID>' stackscan-mcp npx -- -y @stackscan/mcp-serverGemini settings.json에 StackScan MCP 설치
~/.gemini/settings.json
{
"mcpServers": {
"stackscan-mcp": {
"command": "npx",
"args": [
"-y",
"@stackscan/mcp-server"
],
"env": {
"STACKSCAN_API_TOKEN": "<YOUR_STACKSCAN_API_TOKEN>",
"STACKSCAN_TENANT_ID": "<STACKSCAN_TENANT_ID>"
}
}
}
}StackScan MCP 도구 6
README에서 감지됨check_creditslookup_companylookup_domain_technologieslookup_technologylookup_companieslookup_domains_technologies
| check_credits | — | |
| lookup_company | — | |
| lookup_domain_technologies | — | |
| lookup_technology | — | |
| lookup_companies | — | |
| lookup_domains_technologies | — |
구성
STACKSCAN_API_TOKEN필수비밀API token from the StackScan dashboard, My Account -> API Tokens.
STACKSCAN_TENANT_ID필수Workspace UUID, shown on the same page as the token.
STACKSCAN_SESSION_LOOKUP_CAPMaximum credit-consuming lookups per session. Defaults to 25.
| 이름 | 설명 | 유형 |
|---|---|---|
| STACKSCAN_API_TOKEN | API token from the StackScan dashboard, My Account -> API Tokens. | 필수비밀 |
| STACKSCAN_TENANT_ID | Workspace UUID, shown on the same page as the token. | 필수 |
| STACKSCAN_SESSION_LOOKUP_CAP | Maximum credit-consuming lookups per session. Defaults to 25. |
자동 검사
2026년 11월 13일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 이는 보안 감사가 아닙니다. 코드를 직접 읽고 서버에 필요한 최소한의 권한만 부여하십시오. 검사 방식
- 소스 저장소 연결 및 접근 가능stackscan/stackscan-mcp is public and reachablegithub.com/stackscan/stackscan-mcp ↗통과
- 패키지가 이 저장소를 소스로 명시@stackscan/mcp-server names stackscan/stackscan-mcp as sourcenpmjs.com/package/@stackscan/mcp-server ↗통과
- 빌드 출처(Sigstore 증명)No build attestation published for this release검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-10-02github.com/stackscan/stackscan-mcp ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음No popular package one edit away from @stackscan/mcp-server통과
- 패키지 및 해당 종속성에 중요한 보안 권고 없음4 resolved dependencies checked; no critical advisoryosv.dev ↗통과
- 모델에 대한 숨겨진 지침 없음6 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기StackScan MCP server
Ask your assistant what a website runs, and who is behind it.
A Model Context Protocol server for the StackScan Tech Lookup API. Point Claude, Cursor, or any other MCP client at it and you can ask things like:
What is example.com built on?
Who's behind vercel.com? Where are they, what industry, what's their LinkedIn?
How many sites run Klaviyo, and in which countries?
Read-only by design. Nothing here writes to any system of yours.
Install
You need a StackScan account. Sign in, open API Tokens in the dashboard, create a token, and copy your workspace UUID from the same page.
Claude Desktop (extension)
Download stackscan.mcpb from the
releases page, then drag it onto
Settings > Extensions. It asks for your API token and workspace ID and installs the
rest itself.
Claude Desktop (manual config)
Settings → Developer → Edit Config, then add:
{
"mcpServers": {
"stackscan": {
"command": "npx",
"args": ["-y", "@stackscan/mcp-server"],
"env": {
"STACKSCAN_API_TOKEN": "your-token",
"STACKSCAN_TENANT_ID": "your-workspace-uuid"
}
}
}
}
Restart Claude Desktop. The tools appear under the connectors icon.
Claude Code
claude mcp add stackscan \
--env STACKSCAN_API_TOKEN=your-token \
--env STACKSCAN_TENANT_ID=your-workspace-uuid \
-- npx -y @stackscan/mcp-server
Cursor, Windsurf, and others
Same shape: command: npx, args: ["-y", "@stackscan/mcp-server"], and the two
environment variables. Check your client's own MCP docs for where its config file lives.
Tools
| Tool | What it does | Cost |
|---|---|---|
check_credits |
Remaining balance and this month's allocation | free |
lookup_company |
The company behind a domain: name, industry, city, country, LinkedIn, estimated revenue band | 1 credit |
lookup_domain_technologies |
Technologies on ONE domain, in full: category and global usage for each (limit, default 50, max 100), plus how many are paid (premium) products and the estimated monthly tech spend |
1 credit |
lookup_technology |
How many sites run a technology, and where they are | 1 credit |
lookup_companies |
The companies behind up to 20 domains, as a compact table | 1 credit per domain with data |
lookup_domains_technologies |
The technologies on up to 20 domains, as a compact table. Optional category filter |
1 credit per domain with data |
A lookup that finds nothing is not charged. Neither is check_credits.
Breadth vs depth
There are two technology tools and they answer different questions.
lookup_domains_technologies is the breadth view: many domains, technology
names only, ideal for "which of these run Shopify?". lookup_domain_technologies
is the depth view: one domain, every technology with its category and how many
sites use it globally. The batch tool reports how many technologies it left out per
domain, so the model can offer to drill in.
Why the batch tools stop at 20
The REST endpoints behind them take 100 domains per request, and these tools deliberately do not. A tool result goes straight into the model's context, and a hundred full company payloads is tens of thousands of tokens, which crowds out the conversation you are actually having, and the model then has to re-read all of it to answer anything. Twenty compact rows is a table a model can reason over.
It also refuses rather than truncates. If a batch would cost more than your session cap allows, it charges nothing and tells you how many you can afford. Quietly dropping domains would hand back an answer that looks complete and is not.
If you genuinely need hundreds of domains, that is what the REST endpoint is for.
Configuration
| Variable | Required | Default | Notes |
|---|---|---|---|
STACKSCAN_API_TOKEN |
yes | none | Dashboard → API Tokens |
STACKSCAN_TENANT_ID |
yes | none | Your workspace UUID, same page |
STACKSCAN_API_BASE |
no | https://api.stackscan.com |
Rarely needed |
STACKSCAN_SESSION_LOOKUP_CAP |
no | 25 |
See below |
The session cap is a spend cap, and it is deliberate
StackScan's own limit is a rate limit: requests per minute. That stops a burst. It does nothing to stop a patient agent quietly spending an entire credit balance over an afternoon, which is a failure mode humans clicking buttons do not have.
So this server keeps its own counter: 25 credit-consuming lookups per session by
default, after which it refuses and says why. Misses and check_credits never count
against it, because they are never charged. Every successful result carries a footer
showing lookups remaining and your last known balance, so the model can pace itself
instead of discovering the limit by hitting it.
If you mean to go higher, raise it deliberately ("STACKSCAN_SESSION_LOOKUP_CAP": "200") rather
than finding out afterwards.
Development
npm install
npm run build
test-stdio.mjs is a minimal JSON-RPC client that drives the server over a real stdio
pipe, so you can exercise it without an MCP host:
export STACKSCAN_API_TOKEN=...
export STACKSCAN_TENANT_ID=...
node test-stdio.mjs check_credits lookup_company:stripe.com
Never write to stdout in this server. stdout is the JSON-RPC channel; anything else on it corrupts the protocol. Diagnostics go to stderr.
Notes for anyone reading the source
Three things about the upstream API shaped this code and are easy to get wrong:
A miss is HTTP 200, not 404. The API answers "no data for that domain" with
200 {"success": false, "error": "No data available"}. A client that trusts the status
code reads the absent payload and crashes. Every response goes through one place that
separates a miss from a failure, so only a real failure is reported as an error.
Cached responses are still charged. The API's response cache shields its database, not your wallet: a repeat lookup inside the cache window costs the same credit. That is why the local balance decrements on every hit instead of trying to guess which calls were free.
Two base URLs are live. The API's home is api.stackscan.com/v1/.... The older
app.stackscan.com/api/v1/... paths are still served and are deliberately not
redirected, because a redirect would drop the body on POST. If your config still names
the old host, this server detects it and keeps using the old path shape, so upgrading
will not break you.
Privacy Policy
StackScan's privacy policy is at www.stackscan.com/privacy. What it means for this server specifically:
What is collected. The domains and technology names you look up, sent to
api.stackscan.com over HTTPS along with your API token and workspace ID. Nothing else
leaves your machine. This server reads no files, opens no ports and keeps no local
store; the only state it holds is a lookup counter and a credit balance, both in memory
and both gone when the process exits.
How it is used and stored. Lookups are logged against your workspace so credits can be metered and the account can be supported. Results come from StackScan's own crawl data, not from anything you send.
Third parties. Query terms are not sold or shared for advertising. They reach the infrastructure providers StackScan runs on, as set out under "Sharing With Service Providers" in the policy, and nowhere else.
Retention. Covered under "Data Retention" in the policy. Delete your account and the associated lookup history goes with it.
Contact. hello@stackscan.com, or www.stackscan.com/contact.
Links
License
MIT. See LICENSE.
The licence covers this client only, roughly 500 lines that make HTTP requests. The StackScan data it reaches is a paid service and is not covered by it.
StackScan MCP 질문
StackScan MCP를 Claude Code에 추가하려면 어떻게 하나요?
터미널에서 claude mcp add --env 'STACKSCAN_API_TOKEN=<YOUR_STACKSCAN_API_TOKEN>' --env 'STACKSCAN_TENANT_ID=<STACKSCAN_TENANT_ID>' stackscan-mcp -- npx -y @stackscan/mcp-server를 실행합니다. 모든 프로젝트에서 사용할 수 있게 하려면 --scope user를 추가합니다.
StackScan MCP를 Cursor에 추가하려면 어떻게 하나요?
~/.cursor/mcp.json를 열고 mcpServers 아래에 서버를 추가합니다. 위 설치 섹션에 표시된 Cursor 구성을 사용합니다.
StackScan MCP는 어떤 도구를 제공하나요?
6개 도구를 제공합니다. 예: check_credits, lookup_company, lookup_domain_technologies, lookup_technology, lookup_companies.
도메인을 통해 기업에 대해 무엇을 알 수 있나요?
기업 이름, 산업군, 도시, 국가, LinkedIn 프로필 및 예상 매출 범위를 확인할 수 있습니다.
서버에서 과도한 크레딧 소모를 어떻게 방지하나요?
에이전트가 전체 잔액을 모두 사용하는 것을 방지하기 위해 세션당 크레딧을 소모하는 조회 횟수를 기본 25회로 제한하는 세션 캡(session cap) 기능이 포함되어 있습니다.
기술 도구 간의 차이점은 무엇인가요?
breadth view(lookup_domains_technologies)는 여러 도메인에 대한 기술 이름을 보여주며, depth view(lookup_domain_technologies)는 단일 도메인에 대한 상세 정보를 제공합니다.