Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add modu-ai/moai-cowork --skill setup-mcp-connectorgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modu-ai/moai-cowork/setup-mcp-connector)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/setup-mcp-connector"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/setup-mcp-connector/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/setup-mcp-connector"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/setup-mcp-connector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 136 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 191 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Agent Snooping · line 155 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Agent Snooping · line 171 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Agent Snooping · line 191 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- medium MCP Rug Pull · line 142 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 144 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00191 | $0.04794 |
| Opus 5 | $0.00096 | $0.02397 |
| Sonnet 5 | $0.00038 | $0.00959 |
| Haiku 4.5 | $0.00019 | $0.00479 |
Grade A, and why
setup-mcp-connector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP 커넥터 셋업 가이드
개요
Drive·Notion·Higgsfield 3커넥터 + 한국 공공데이터·문서·법령 5 MCP(kordoc·dart·korean-stats·archhub·korean-law)를 Cowork에 연결하는 단계별 가이드를 제공합니다. 인증 흐름, API 키 입력, 1회 호출 검증, 트러블슈팅까지 셋업 전 과정을 다룹니다.
셋업 완료 체크리스트
- Drive·Notion·Higgsfield — 인증 성공 + 1회 호출 성공 (Drive: 폴더 list / Notion: 공유 페이지 read / Higgsfield: 모델 list)
- kordoc — Node.js 18+ 확인 + 1회 문서 파싱 성공 (키 불필요)
- dart(korean-dart-mcp) — Node.js 20.19+ + OpenDART 키 + 1회 공시 검색 성공
- korean-stats — 1회 자연어 통계 조회 성공 (키 불필요, 공용키 hosted)
- archhub — 1회 건축물 종합카드 조회 성공 (키 불필요, 공용키 hosted)
- korean-law — 법제처 OC 키 + 1회 법령 검색 성공 (law.go.kr 무료 발급, 사용자마다 키 필요)
트리거 키워드
MCP 커넥터 연결, Drive 인증, Notion Integration Token, Higgsfield API 키, 3커넥터 설치, computer:// 링크, MAX_PATH 오류, 한글 파일명 오류, OAuth redirect URI
워크플로우
Step 1 — 사전 준비물
커넥터 연결 전에 아래 계정을 미리 생성해 두세요:
- Google 계정 (Drive)
- Notion 계정
- Higgsfield 계정 + 워크스페이스 크레딧 충전
[HARD] API 키 보안 수칙: API 키는 본인이 직접 발급·보관합니다. 채팅 대화나 공유 문서에 키 원문을 붙여넣지 말고, 커넥터 설정 화면의 API Key 필드에만 입력하세요.
Connector A — Google Drive
목적: Cowork 폴더 마운트 + 파일 접근 (drive.readonly, drive.file 권한)
인증 방법: Cowork 앱 → 커넥터 추가 → Google Drive → OAuth 로그인
필수 권한
drive.readonly— 파일 읽기drive.file— Cowork가 생성한 파일 접근
인증 단계
- Cowork 앱 → 설정 → MCP 커넥터 → Google Drive 선택
- "Google 계정으로 연결" 클릭
- Google OAuth 화면에서 계정 선택 + 권한 허용
- 연결 완료 후 Drive 폴더 list 1회 호출로 검증
1회 호출 검증: 폴더 목록이 응답에 나타나면 성공
Connector B — Notion
목적: 작업 결과물 Notion 페이지 읽기·쓰기
인증 방법: Cowork 앱 → 커넥터 추가 → Notion → OAuth 인증
인증 단계
- Cowork 앱 → 설정 → MCP 커넥터 → Notion 선택
- "Notion으로 연결" 클릭
- Notion OAuth 화면에서 워크스페이스 선택 + 페이지 접근 권한 허용
- 연결 완료 후 공유 페이지 read 1회 호출로 검증
1회 호출 검증: 공유 페이지 내용이 응답에 나타나면 성공
Connector C — Higgsfield
목적: 광고 영상 생성 등 미디어 작업 (이미지·영상 생성 모델 호출)
인증 방법: API 키 방식 (OAuth 아님)
사전 확인 사항
- Higgsfield 워크스페이스 크레딧 충전 여부 확인 (잔액 부족 시 인증은 성공해도 생성 호출이 실패할 수 있음)
- 예상 사용량 가늠: 영상 1편(5-10초) 기준 크레딧 소모량을 미리 확인
- 비용 한도: 워크스페이스 설정에서 사용 한도를 지정해 예상 외 과금 방지
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 345 lines · 191 tokens per session scan A b4d90b00ef65
setup-mcp-connector is a skill published in the GitHub repository modu-ai/moai-cowork (300 stars, last pushed 8d ago), licensed Apache-2.0. It adds 191 tokens to every session and 4,794 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
market-intelligence-report
Produce a Market Intelligence Report — YouTube competitive research, channel analysis, content gap discovery, idea generation, daily scanning, and AI trend scouting — then render it as a BenAI-branded HTML dashboard in the instant-ui design language. Use this skill whenever the user says "market intelligence report"…
linkedin-writer-vault
Vault-aware LinkedIn writer. Same step-by-step LinkedIn post process as linkedin-writer, but ICP, voice, and offer context come from the vault's Context/ folder instead of being bundled inside the skill. Update one file in the vault and every skill pointing to it inherits the change. TRIGGERS: LinkedIn post, LinkedIn…
operator
Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…
crm-prospect-mining
Mine high-value prospects from CRM pipeline stages (Lost, No Show, Churned, Stalled) by cross-referencing records with LinkedIn company data and comms history. Connects to any CRM, pulls records from target stages, filters out personal email domains, finds company LinkedIn pages via web research, bulk-scrapes company…
marketing-os-carousel
Build an image-first social carousel from an asset already filed in the Marketing OS, export it as a PDF, and record it back as a real channel asset. Brand palette, typography, the logo pointer and the never-black-background rule all resolve from Context/brand/brand-kit.md. Source is a filed newsletter edition…
seo-hreflang
Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations for HTML, HTTP headers, and XML sitemaps. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region"…