Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Checks the most important factual claims in AI output against live web sources by default.
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.
X-API-Key비밀로 표시된 값은 내 계정의 열쇠예요. 절대 다른 사람과 공유하거나 채팅에 붙여 넣지 마세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
터미널에서 이 명령어를 실행하세요
claude mcp add --transport http faultline https://faultline-api.fly.dev/mcp --header 'X-API-Key: your-value'실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"faultline": {
"url": "https://faultline-api.fly.dev/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"faultline": {
"type": "http",
"url": "https://faultline-api.fly.dev/mcp",
"headers": {
"X-API-Key": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 주소는 요청 header에 키가 필요한데, 커넥터 추가 메뉴에서는 넣을 수 없어요. 대신 Claude Code, Cursor, VS Code를 쓰세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
X-API-Key 비밀 필수 HTTP header이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
서버가 도구 목록을 보여 주기 전에 로그인을 요구해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 8일 점검
레지스트리 이름이 GitHub 계정 nxtg-ai 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
323ms 만에 응답(HTTP 401)
키나 토큰을 직접 복사해서 붙여 넣어야 해요
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 3개 중 2개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
입력해야 할 값: X-API-Key
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(0.12.1)은 3일 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, Hominoport
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:↓ 주간 다운로드i★ 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.
A human nominee and body in the physical world for autonomous agents. Signed public offer.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Future-proof your agent stack. Independent of every model vendor: NXTG.ai does not build the models Faultline checks.
Faultline decomposes AI-generated output into atomic claims, verifies each against live evidence, and can fail a CI build on the result.
Release stage: alpha. Usable today, with sharp edges. No accuracy figure is claimed: verdict accuracy has not yet been re-graded independently. Anything may change before 1.0.
The hosted API ships three governance records as code: a risk register export (POST /scan/risk-register), a tamper-evident audit log manifest (GET /audit/log/manifest, admin keys only), and human sign-off records (POST /scans/:id/approve, GET /scans/:id/approvals). In the manifest, each chain hash is the SHA-256 of the entry hash followed by the previous chain hash. You can recompute the chain with openssl dgst -sha256 alone, with no Faultline tooling.
| Item | State | How checked |
|---|---|---|
| CLI on npm | @nxtg/faultline 0.11.1 | npm view @nxtg/faultline version |
| Hosted API | https://faultline-api.fly.dev, version 0.11.1 | curl https://faultline-api.fly.dev/health |
| Web app | https://faultline.nxtg.ai (separate repo, faultline-web, on Vercel) | live pricing page read 2026-10-01 |
| Plans | Free 5 scans/month. Personal $19/mo, 100 scans. Pro $49/mo, 500 scans. Enterprise: custom, scan allowance set in the contract | https://faultline.nxtg.ai/pricing |
| Multi-model consensus | Enterprise only. The API returns 403 consensus_not_in_plan to any caller below Enterprise, before the stream opens | packages/api/src/plugins/consensus-entitlement.ts; live check by fp 2026-10-01 (pro, personal and free 403, enterprise 200, mock provider) |
POST /critique | Needs an API key. Rate limited. Covered by the provider-spend cap and written to the spend ledger | packages/api/src/routes/critique.ts |
| Provider-spend cap | $100/month. The ledger records every managed scan and critique. Enforcement ships dormant (FAULTLINE_PROVIDER_SPEND_CAP=on turns it on) and is off in production | docs/provider-spend-cap.md; GET /usage showed providerBudget.enforced=false on 2026-10-01 |
| Per-key monthly scan cap (API side) | Dormant (FAULTLINE_USAGE_CAP). Plan limits above are enforced by faultline-web | docs/usage-cap.md |
| Capability | Description |
|---|---|
| Atomic claim extraction | Decomposes AI output into fact / opinion / interpretation with importance scoring |
| Per-claim verification | Verdict: supported / contradicted / mixed / unverified + confidence score |
| Scan comparison | POST /scan/compare + faultline compare — new/removed claims, verdict changes, trust score delta |
| CI gate | faultline compliance-report --ci exits 1 when the scan's overall risk is high or critical, an article check in the report has failed, the report's domain checklist item has not passed, or the report score is below --threshold; --strict also fails on partly met article checks and on checklist items not assessed. Otherwise it exits 0 |
| Weakest-link detection | Per-claim fragility scoring — finds the claim that most undermines the argument |
| Claim dependency graph | Mermaid and Graphviz DOT visualizations |
| Rules engine | YAML-defined rules; built-in PII, bias, toxicity rulesets |
| CI gate | --fail-on high returns exit code 1; SARIF output for GitHub Code Scanning |
| Enterprise API | REST API (about 190 routes) with key management, audit trail, rate limiting, webhooks, batch scanning, caching |
| Provider failover | Automatic chain Gemini → OpenAI → Claude → Perplexity; circuit breaker with 5-min cooldown |
| Monitoring | GET /health/deep, GET /metrics (Prometheus), GET /status (HTML dashboard) |
| Scheduled jobs | POST /jobs — recurring scans on a cron schedule with webhook delivery |
| Integrations | Python client source in sdks/python, MCP server packages/mcp, Terraform provider packages/terraform-provider, GitHub Action nxtg-ai/faultline-action (see SDKs) |
| Multi-tenant | Tenant CRUD, API key association, per-tenant usage aggregation |
| Cost tracking | Per-scan token/cost estimation; GET /costs with provider/tenant/date filters |
| Scan history | GET /scans/search — full-text across your API key's past scans (admin key: all), cursor pagination |
| Rule templates (HIPAA, SOX, FERPA, Gov) | HIPAA / SOX / FERPA / Gov templates; POST /scan/compliance/:template |
| Bulk import | POST /scan/bulk — ZIP of documents, async job, GET /jobs/:id/progress |
| Swagger UI | GET /docs — interactive OpenAPI 3.0 spec with Try-it for every endpoint |
| Claim explainability | GET /claims/:id/explain — reasoning chain, evidence found, actionable suggestions |
| Scan diff | POST /scan/diff — scan two texts, inline diff (added/removed/changed/unchanged) |
| Deadline list | GET /compliance/deadlines — a list of upcoming regulatory dates with days until each; no assessment |
| Deadline keyword check | POST /compliance/scan-check — match claim text against keywords tied to those dates |
| i18n | Accept-Language: es/fr/en — localized error messages and report labels (EN/ES/FR) |
| Property-based tests | fast-check oracle coverage: confidence bounds, dedup invariants, cost aggregation, sort stability |
| GDPR data requests (Article 15 export, Article 17 erasure) | Article 15 export (GET /tenants/:id/export → ZIP) + Article 17 erasure (DELETE /tenants/:id/data) covering scan history, audit log, notifications, webhooks, costs, schedules |
| Multi-model consensus | POST /scan/stream with pipelineConfig.consensus: true. Enterprise only, enforced server-side (403 below Enterprise) |
| Claim critique | POST /critique: critique plus improved prompt for failed claims; API key, rate limit and provider-spend cap apply |
| Real-time scan streaming | GET /scan/stream?text=...&provider=mock — Server-Sent Events; progressive per-claim delivery via onClaimVerified callback; streams start → claim_verified × N → complete; no polling required |
| Mutation-tested core | Stryker gate (CRUCIBLE Gate 6, threshold 80%): cli/scan.ts 81.97%, stream.ts 88.64%, compliance-report.ts 80.81%, GDPR stores 80.94% to 96.81%. Last measured 2026-03-21 to 2026-04-17 per docs/mutation-testing.md; not re-run since |
| Provider | Requires | Best For |
|---|---|---|
| Gemini | GEMINI_API_KEY | Live web grounding (free key available) |
| Perplexity | PERPLEXITY_API_KEY | Real-time search-native verification |
| OpenAI | OPENAI_API_KEY | Training-data verification, GPT ecosystem |
| Claude | ANTHROPIC_API_KEY | Training-data verification, reasoning-heavy docs |
| Mock | None | CI pipelines, unit tests, offline development. Returns synthetic verdicts and verifies nothing; the CLI never falls back to it silently |
Switch providers with --provider . No code changes required. With no provider key and no FAULTLINE_API_KEY, the CLI says nothing was checked and exits instead of inventing a verdict (since v0.10.1). With FAULTLINE_API_KEY set, guard and the MCP server run the scan on the hosted API with server-side provider keys.
faultline scan --file document.pdf or POST /scan/upload; powered by pdf-parse + tesseract.js--input doc.txt--dir ./docs --glob "*.md"POST /scan/reportjson — programmatic processing, CI pipelinesmarkdown — PRs, reports, documentationhtml — browser-readable audit reportssarif — VS Code Problems panel, GitHub Code Scanning (--sarif shorthand writes results.sarif)POST /keys, GET /keys, GET /keys/:id, PATCH /keys/:id, DELETE /keys/:id; soft-disable/enable; scoped permissions (scan / report / upload / admin / pro)GET /keys/dormant), expiry notifications (7d/1d thresholds), bulk delete/disable/enable, usage analytics (GET /keys/usage), hygiene dashboard (GET /keys/usage/view)GET /audit/log (query + filter), GET /audit/log/stats, GET /audit/log/export (NDJSON); tenant-scoped viewGET /usage (admin keys also see the provider-spend budget)X-RateLimit-* headers402) and a fleet provider-spend cap (503), both dormant until switched on; the spend ledger records every managed scan and /critique call either wayPOST /tenants); all resources scoped by tenant: scan history, notifications, webhooks, audit log; GET /tenants/:id/usageGET /costs (keyId/provider/date filters + aggregate)GET /dashboard: live scan feed, provider health, active keys, scan counts (today/week/month), risk distributionPOST /webhooks; scan.complete / scan.failed / job.complete events; HMAC-SHA256 signing; per-webhook retry config (maxAttempts 1–5, retryDelayMs); rate limiting (FAULTLINE_WEBHOOK_RATE_LIMIT); circuit breaker (FAULTLINE_WEBHOOK_CIRCUIT_THRESHOLD/COOLDOWN_MS); delivery log + dashboardPOST /scan/batch (1–10 texts, concurrent, partial failure semantics); see docs/ci-integration.mdPOST /scan/compare: diff two scan results (new/removed claims, verdict changes, trust score delta)FAULTLINE_CACHE_TTL_MS); X-Cache: HIT/MISS header; GET /cache/stats, DELETE /cachePOST /jobs: recurring scans on a */N * * * * cron schedule; results dispatched to webhookUrl503 when all providers downGET /scans/search?q= full-text; stale scan detection (GET /scans/stale); usage analytics (GET /scans/usage); bulk pruning (DELETE /scans/stale); hygiene dashboard; faultline scans CLIPOST /scan/compliance/:template; custom template uploadPOST /scan/bulk (ZIP of documents → async job); GET /jobs/:id/progress (percentage + per-file status + summary)GET /health/deep (subsystem status + provider config flags), GET /metrics (Pro앞부분만 보여 드려요. 나머지는 저장소에서 읽어 보세요