Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
제작자가 쓴 설명(영어 원문)
Security checks for AI agents and MCP configs: 124 tested checks, from your AI coding assistant.
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.
AGENTVERIFY_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.
Claude Desktop → Settings → Developer → Edit Config를 열고 claude_desktop_config.json에 이 내용을 붙여 넣으세요
{
"mcpServers": {
"agentverify": {
"command": "npx",
"args": [
"-y",
"agentverify",
"mcp"
],
"env": {
"AGENTVERIFY_API_KEY": "your-value"
}
}
}
}터미널에서 이 명령어를 실행하세요
claude mcp add agentverify --env AGENTVERIFY_API_KEY=your-value -- npx -y agentverify mcp실행하기 전에 빈 값을 채워 주세요.
프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"agentverify": {
"command": "npx",
"args": [
"-y",
"agentverify",
"mcp"
],
"env": {
"AGENTVERIFY_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": {
"agentverify": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentverify",
"mcp"
],
"env": {
"AGENTVERIFY_API_KEY": "your-value"
}
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
이 서버는 내 컴퓨터에서 실행되는데, ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요. 다른 앱을 고르세요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
내 컴퓨터에서 실행돼요. 설치하면 AI 앱에 도구 목록이 나타나요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 7일 점검
레지스트리 이름이 GitHub 계정 AI-Blockchain-Ventures 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
내 컴퓨터에서 실행되는 서버라 인터넷 엔드포인트가 없어요
내 컴퓨터에서 실행되며, 대신 로컬 설정을 사용해요
내 컴퓨터에서 실행돼요. 도구 목록은 인터넷 엔드포인트가 있는 서버에서만 읽을 수 있어요
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.
입력해야 할 값: AGENTVERIFY_API_KEY
내 컴퓨터에서 실행돼요. AI 앱이 필요할 때 실행하고, 데이터는 제작자의 서버를 거치지 않아요(서버 자체가 온라인 서비스를 호출하는 경우는 제외).
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(2.0.0)은 3일 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. 내 컴퓨터에 Node.js도 있어야 해요.
같은 카테고리에는: Spec Driven Development, Remote Desktop Commander, Rystic
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.
Start, seed, clock, inspect and diff Rystic API simulators from your agent.
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Know what your AI agent can do before you deploy it.
Agent Verify inspects an AI agent or agent package — its permissions, tools, MCP connections, execution controls, secrets, runtime configuration, and dependencies — and issues a VERIFIED or NOT VERIFIED result with evidence, before the agent reaches production.
Traditional security tools scan software. Agent Verify also examines what an AI agent is *connected to* and what those connections may let it actually *do* — a legitimate credential, valid API access, and an approved tool can still combine into an action the agent should never be able to take.
Agent Verify provides open-source CLI, CI, web integration, and API tooling backed by a proprietary verification engine — see Privacy & proprietary scanner boundary.
Dashboard ─┐
CLI ───────┼──► Worker API ──► server-side entitlement & scan quota ──► private scanner engine API ───────┘ │ └──► D1 (billing/quota) · Firestore (reports, orgs, audit log)
Every scan — from the dashboard, the CLI, or a direct API call — goes through the same authenticated Worker route and the same server-owned monthly quota; there is no client-only or local-storage-based scan counter anywhere in the product, and no browser code ever runs the detection engine directly. See Web App and Privacy & proprietary scanner boundary for how that boundary is enforced and verified.
| Component | Location | License |
|---|---|---|
| Web app (dashboard, reports, landing page) | apps/web | Open source (this repo, MIT) |
CLI / SDK (agentverify on npm) | packages/cli | Open source (this repo, MIT) |
| Cloudflare Worker API | workers/api | Open source (this repo, MIT) |
Detection engine (@agentverify/scanner) | packages/scanner | Proprietary — not in this repository |
npm install -g agentverify
agentverify scan ./agents --key av_your_key
Get an API key from Dashboard → API access after signing in at https://aimodularity.com/agentverify/. Full docs, including the API contract, CI/CD integration, and JSON output shape: https://aimodularity.com/agentverify/docs/
agentverify --help
agentverify --version agentverify scan ./agents --key av_your_key # scan a directory agentverify scan --file agent.json --key av_your_key # scan a single file agentverify scan ./agents --key av_your_key --ci # CI mode, strict exit codes agentverify scan ./agents --key av_your_key --ci --policy standard # + policy evaluation
CI exit codes distinguish a real security failure from an execution problem:
| Code | Meaning |
|---|---|
0 | All scanned files verified |
1 | NOT_VERIFIED — a real security/verification failure |
2 | NOT_ASSESSED — insufficient evidence for a verdict |
3 | Execution error — bad/missing API key, network failure, missing file (not a security finding) |
- uses: AI-Blockchain-Ventures/agentverify@v1.4.0
with: path: ./agents api-key: ${{ secrets.AGENTVERIFY_API_KEY }}
See docs/github-action.md for the full reference — Markdown/JSON output modes, PR comment posting, branch protection, and policy evaluation in CI.
The dashboard (apps/web) provides scan history, report sharing, a check catalog, policy profiles, and organization/team management (roles: Owner/Admin/Member/Viewer) on top of the same Worker API the CLI uses — every dashboard scan is server-metered exactly like a CLI or API scan, never run or counted client-side.
Permissions and tool access, MCP server connections and what they expose, execution/authorization controls, secrets and credential handling, runtime configuration, and dependencies — static analysis of submitted content, not a live sandbox execution.
Every finding is also labeled by how it was derived: definite (a concrete pattern was matched), heuristic (inferred from context — could be a false positive/negative), or informational (a neutral observation). Agent Verify does static analysis — it never executes submitted code — so it is honest about what it cannot see: see Limitations below.
Every scan computes a SHA-256 artifact fingerprint over the exact scanned content — identical content always produces the same fingerprint, independent of when it ran or whether the ruleset changed since. When server-side signing is configured, a scan result can carry a signed attestation (ECDSA P-256 / ES256) over the verdict, score, and fingerprint — independently verifiable by any third party with nothing more than the published public key, with no shared secret and no need to trust Agent Verify's API at verification time.
Built-in policy profiles (standard, high-security, financial-agent, production-infrastructure) can be evaluated against a scan's evidence in addition to — never instead of — the base verdict: a scan can be VERIFIED and still fail a stricter policy, but a policy can never turn a NOT_VERIFIED scan into a pass. Pass --policy on the CLI or the policy input on the GitHub Action.
Billing, quota, and authentication are server-authoritative — see docs/billing-setup.md for the full architecture. Webhook payloads are signature-verified and processed idempotently, organization mutations are RBAC-enforced server-side (never trusting a client-supplied role), and Firestore Security Rules enforce per-user access control independently of the UI. Full detail and how to report an issue: SECURITY.md.
The detection engine — the actual rules that decide what's risky — is Agent Verify's core IP and is intentionally not tracked in this git repository (packages/scanner/ is gitignored). The CLI and Worker call it over HTTPS or via a private build; nothing in this public repo bundles or exposes its source, and no browser-shipped code ever imports it — only Worker-side (server-only) code does. A permanent CI check (npm run check:private-boundary) builds the web app and statically inspects every emitted client bundle for known proprietary markers on every change, so this boundary can't silently regress. Public CI validates the web app, CLI, and Worker against a type-compatible stub of the scanner (see scripts/create-ci-scanner-stub.mjs) so the public build is verifiable without the private engine ever being present.
Free (10 scans/month, basic findings, private report history), Pro ($19.99/month — full remediation guidance, corrected snippets, A2SPA implementation guidance, PDF export, 100 scans/month), Team (coming soon), Enterprise (contact us). Pricing is defined once in apps/web/src/lib/pricing.ts and mirrored in the Worker's quota table (workers/api/src/billing.ts) — see those files for the current source of truth.
npm install
npm run dev # apps/web dev server npm run build # apps/web production build npm run build:cli # packages/cli npm run build:worker # workers/api npm run lint # apps/web npm run check:web # apps/web typecheck npm run check:worker # workers/api typecheck npm run test:worker # workers/api tests npm run test --workspace=packages/cli npm run test:rules # Firestore Security Rules against the real emulator npm run check:private-boundary # proprietary-boundary regression check
See CONTRIBUTING.md for the full contributor guide, including what you can and cannot modify and PR expectations.
Agent Verify performs static analysis of submitted content. It does not execute your agent and cannot see: runtime-only behavior, permissions/credentials granted dynamically at deploy time, remote policy enforced outside the codebase, production network ACLs, external identity provider policy, or runtime secrets injected outside the source. Every report includes a "What Agent Verify Could Not Determine" section stating this explicitly for that scan. Findings are evidence-based and heuristic, not a formal proof of security — a clean report is not a guarantee of safety, and a finding is not proof of exploitation.
MIT — AI Blockchain Ventures LLC — hello@aiblockchainventures.com
MIT applies to the components in this repository (web app, CLI, Worker API) as listed above. The detection engine is proprietary, is not distributed under this license, and is not included in this repository.