Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Read-only MCP server for wafergraph.com's semiconductor & AI supply-chain data: 30 tools, no auth.
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://wafergraph-mcp.jwpalm99.workers.dev/mcp터미널에서 이 명령어를 실행하세요
claude mcp add --transport http wafergraph https://wafergraph-mcp.jwpalm99.workers.dev/mcp프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"wafergraph": {
"url": "https://wafergraph-mcp.jwpalm99.workers.dev/mcp"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"wafergraph": {
"type": "http",
"url": "https://wafergraph-mcp.jwpalm99.workers.dev/mcp"
}
}
}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://wafergraph-mcp.jwpalm99.workers.dev/mcp메뉴 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.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 6일 점검
레지스트리 이름이 도메인 wafergraph.com 기준으로 확인되었어요(레지스트리가 도메인 소유를 확인해요)
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 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(1.2.0)은 3개월 전 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: Spec Driven Development, Remote Desktop Commander, HotCodePush
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
A remote MCP server exposing wafergraph.com's semiconductor & AI supply-chain dataset — 565 companies across 12 segments, the supplier/customer graph, and a 74-deal M&A corpus — as 30 read-only tools any MCP-speaking AI agent can call directly.
No auth, no cost, read-only. Streamable HTTP transport at /mcp. Human landing page at /.
Live: https://mcp.wafergraph.com
| Tool | Purpose |
|---|---|
search_companies({query?, segment?, country?}) | Name/description search with segment & country filters. Compact list, capped at 25, with a total match count. |
get_company({id}) | Full allowed profile for one company (by id or name) plus its supplier/customer edges. |
get_segments() | The 12-segment taxonomy (+ subsegments, market_position enum) with live company counts. |
get_supply_chain({id, direction, depth}) | Walk the supplier/customer graph from a focal company up to 2 tiers up ("up"), down ("down"), or "both". |
get_deals({query?, segment?}) | Search the M&A deal corpus. Compact list, capped at 30, with a total match count. |
compare_companies({ids}) | Side-by-side comparison of 2-6 companies on aligned fields, plus their shared and unique supply-chain counterparties. |
get_country_exposure({segment?}) | Geographic concentration: which countries host a segment's companies, ranked by count, with disclosed market-cap coverage. |
find_chokepoints({segment?, limit?}) | Rank chokepoints by downstream dependency weighted by market position. Transparent heuristic, not a proprietary risk model. |
analyze_portfolio_exposure({holdings}) | Map tickers or ids to segment/country exposure and flag suppliers that several holdings share. Not investment advice. |
| Tool | Purpose |
|---|---|
filter_companies({...}) | Structured multi-criteria screen (segment, subsegment, country, position, public, market-cap band, has_ticker) with sorting and pagination. |
list_subsegments({segment?}) | Every subsegment with its live company count and parent segment. |
get_subsegment({segment, subsegment}) | All companies in one subsegment with position and country breakdowns. |
find_similar_companies({id}) | Nearest structural neighbours by Jaccard similarity over segment tags and shared supply-chain counterparties. |
rank_by_market_cap({segment?, country?, limit?}) | Largest companies by disclosed market cap, always with its coverage ratio. |
resolve_ticker({inputs}) | Batch-resolve up to 25 tickers, names, or ids to canonical companies, with suggestions on a miss. |
| Tool | Purpose |
|---|---|
list_countries({segment?}) | Every country with company counts, segment mix, and public/private split. |
get_country_profile({country}) | One country in depth, including how many supply relationships cross its border in each direction. |
compare_countries({countries}) | 2-5 countries side by side, with uniquely-present and dominant segments. |
get_segment_leaders({segment?}) | Who occupies the monopoly and leader positions in a segment. |
get_upstream_concentration({id}) | One company's supplier mix by country and segment with an HHI index and edge-coverage context. |
| Tool | Purpose | ||
|---|---|---|---|
find_paths_between({from, to, max_depth?}) | Documented supply paths between two companies, shortest first. | ||
| `simulate_disruption({company_id? | country? | segment?})` | Blast radius if a company, country, or segment goes offline, ranking those left with no documented alternative. |
find_single_source_dependencies({segment?, country?}) | Customer/subsegment pairs served by exactly one documented supplier. | ||
rank_by_connectivity({metric?, limit?}) | Rank by documented degree. Measures documentation density, not real-world criticality. | ||
| `find_common_suppliers({ids? | segment?})` | Suppliers shared across an arbitrary set of companies, with the share of the set each serves. |
| Tool | Purpose |
|---|---|
get_deal({id}) | One M&A deal in full, with parties resolved to companies where possible. |
find_deals_by_company({id}) | Every deal a company took part in, split by role, with the match method exposed. |
get_ma_activity_summary() | Deal counts and disclosed values by year, type, and status. |
find_consolidation_hotspots() | Which segments are consolidating, with unresolvable deals counted rather than dropped. |
get_dataset_stats() | What this dataset contains, how fresh it is, and where it is thin. Call it to learn what the data cannot answer. |
Every response includes:
data — the payload.attribution — compiled-by/sources block (SEC, Wikidata, Wikipedia, GLEIF) plus a company_url back to the full sourced profile on wafergraph.com.links — { report, newsletter } pointing back to wafergraph.com and its hand-scored Vendor Exposure Review.Company records include key_products as of 2026-07-19. That field in wafergraph's own dataset was originally bulk-drafted with a known fabrication/mis-scope history and was withheld here until a verified deep-fill landed upstream; it now has (confirmed live) 564/565 companies filled, with only sk_enpulse empty (defunct, absorbed into SKC 2025-12-23). Every field shipped here — name, ticker, market_cap_usd_b, segments, one_liner, market_position, key_products, key_customers/key_suppliers graph edges, deals — is established, trust-checked data. Fields are still whitelisted (not blacklisted) in src/types.ts (toAllowedCompany), so anything added upstream later stays excluded by default until deliberately added.
Counters only, never identities. No IPs, no query contents or tool arguments, no user identifiers, no cookies, no PII. Specifically: how many times each tool was called per day, how many distinct sessions opened per day, and which client *software* connected (the clientInfo name and version your MCP client already sends in the initialize handshake, e.g. claude-code@2.1.0).
Sessions are not users — one person reconnecting counts several times. Nothing recorded here can identify who you are.
claude mcp add --transport http wafergraph https://mcp.wafergraph.com/mcp
Settings → Connectors → Add custom connector → paste:
https://mcp.wafergraph.com/mcp
{
"mcpServers": { "wafergraph": { "url": "https://mcp.wafergraph.com/mcp" } } }
Cloudflare Worker, TypeScript, built on the agents package's McpAgent (Durable-Object-backed Streamable HTTP MCP server — free on the Workers Free plan; SQLite storage backend). See CLAUDE.md for the file map and the data-source-mode decision (hybrid live-fetch + one vendored snapshot, discovered by E2E-testing the upstream endpoints rather than assumed).
npm install
npm run dev # wrangler dev, local npm run typecheck # tsc --noEmit npm run deploy # wrangler deploy
See ATTRIBUTION.md for the full source/license breakdown (SEC EDGAR public domain, Wikidata CC0, Wikipedia CC BY-SA 4.0 — attribution required, GLEIF). Short version: free to use, credit wafergraph.com, not financial advice.
This is an independent project built against wafergraph.com's public dataset; it is not an official wafergraph product.