youdotcom-oss/risk-analysis-server/import-integration
Claude Code and agent skill by youdotcom-oss/risk-analysis-server
- community
Checking that the SKILL.md file is still in the repository.
Integrate the risk-analysis server into an existing Bun app as a library, attaching your own auth and hosting. Use when you want your own OAuth/IdP flow or custom HTTP stack rather than deploying the repo as-is.
Install
npx vskill@latest install youdotcom-oss/risk-analysis-server/import-integrationSKILL.md
Import the server as a library
The package ships raw TypeScript — a Bun project imports it directly, no build step. The entry points are the exports subpaths in package.json:
@youdotcom-oss/risk-analysis-server/server—createApp(HTTP entry).../mcp—buildMcpServer(tools factory).../pipeline—buildSweepDeps,runSweep,sweepAllProfiles.../db—openDb.../model—getModel.../services/youand.../services/jev— the You.com and Jev clients
Steps
bun add @youdotcom-oss/risk-analysis-server- In your own Bun entry point, build the app with your auth:
- Set the
RISK_ALLOWED_HOSTSenv var to your public hostname(s)
(DNS-rebinding protection rejects unknown Host headers).
- Scheduled sweeps: pass
scheduler(aProfileSchedulerwired with your
sweep implementation) to createApp and either set cronSchedule for a global schedule or let users manage per-profile schedules via the set_sweep_schedule tool. (RISK_CRON_SCHEDULE only applies when running this repo's own entries directly.)
Verify
bun run check && bun test in the consuming project; the exports smoke test (src/tests/exports.spec.ts) in this repo proves the surface resolves.
Gotchas
- The per-request factory in
createAppruns per MCP request — keep the
verifyBearer cheap; it runs on every /mcp call.
- The
verifyBearerreturnsubbecomes the tenant id and the MCP session
user. Pick a stable value (user id or org id), not an email that changes.
- For a full OAuth 2.1 flow instead of bearer HMAC, use the MCP SDK's
verifyBearerToken and the authorization-serving docs: https://ts.sdk.modelcontextprotocol.io/v2/serving/authorization.html
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/import-integration/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/youdotcom-oss/risk-analysis-server/import-integration)