LifeScored MCP Server
Provides access to the rulebook, input schema, and methodology for the life scored system, enabling agents to compute scores locally without sending personal data to the server.
README
life. scored.
You are already a number.
A credit score, an actuarial row, a callback probability — this app rebuilds those numbers in the open: every rule cited or flagged as a guess, every weight visible and editable. Transparency, not judgment.
Stack
- Svelte 5 + SvelteKit, prerendered static pages, deployed to Cloudflare Workers
- One dynamic endpoint:
POST /api/narrative— KV-cached Gemini narratives with a deterministic local fallback (the app is fully functional with no API key at all) - All user data stays in the browser (localStorage + URL-fragment share links)
- Traffic is measured with Cloudflare Web Analytics — cookieless and aggregate; it cannot see your inputs, which never leave your device anyway.
Develop
npm install
npm run dev # app at localhost:5173 (narrative falls back to local composer)
npm test # vitest suite: rulebook invariants, engine, codec, worker handler
npm run check # svelte-check
Deploy (Cloudflare free tier)
Deploys run automatically from GitHub Actions on every push to main
(.github/workflows/deploy.yml): the workflow
runs the full test suite + typecheck, and only then builds and deploys.
One-time setup:
Secrets are kept in hush: stored once in your OS keychain,
then piped straight into the consumer — they never get pasted into a terminal, echoed, or printed.
This project's hush items use a lifescored- prefix so they group together in a keychain search.
(No hush? Drop the hush pipe … -- prefix and run the bare npx wrangler / gh command; hush just
wraps it.) Local dev needs no secrets at all — the narrative falls back to a local composer.
-
Create the KV namespace and paste its id into
wrangler.jsonc:npx wrangler kv namespace create NARRATIVE_KV -
Set the Gemini key as a Worker secret (persists across deploys; optional — omit to run AI-free with the local narrative fallback):
hush set lifescored-gemini-key # paste it once, hidden dialog hush pipe lifescored-gemini-key -- npx wrangler secret put GEMINI_API_KEY -
Give GitHub Actions the deploy credentials (Settings → Secrets and variables → Actions):
hush set lifescored-cloudflare-api-token # "Edit Cloudflare Workers" token hush pipe lifescored-cloudflare-api-token -- gh secret set CLOUDFLARE_API_TOKEN gh secret set CLOUDFLARE_ACCOUNT_ID --body "<your-account-id>" # account id isn't secret
Push to main and the action ships it. To deploy by hand instead:
npm run deploy
Deploy your own
Fork the repo, do the one-time setup above with your own Cloudflare account, and push. The app is fully functional with no Gemini key at all.
Editing the rulebook
Rules live in src/lib/rulebook/<domain>.ts. Each rule is declarative: logic,
evidence tag (SOURCED/SPECULATIVE), citation with access date, a pure
position(inputs) (the measured fact, normalized to a numeric position), declared
bounds (negative floors only where the cited system itself subtracts; the wealth
rules are uncapped above), and a weightRationale justifying its weight against
the 1.0× income baseline; the engine computes points = round(position × weight).
Add a rule, and the UI, weight editor, share
codec, and about-page source list pick it up automatically. npm test enforces
the invariants (bounds, integer scores, citation present).
Use it from an agent (MCP or skill)
The whole rulebook + exact math is published so any agent can compute a score on its own side — nothing about a person is ever sent to lifescored.com.
- MCP server —
com.lifescored/mcpon the official registry; endpointhttps://lifescored.com/mcp(stateless Streamable HTTP, no auth, accepts no personal data). Tools:get_rulebook,get_input_schema,get_methodology,how_to_give_feedback. - Skill — a drop-in
skills/lifescored/skill. Copy it into your agent's skills directory (e.g.~/.claude/skills/). It prefers the MCP and falls back torules.json. - Raw data —
https://lifescored.com/rules.jsonand/llms.txt.
Contributing
Every commit must reference a GitHub issue number, e.g. feat: add presets (#2) or refs #5. A commit-msg hook enforces this automatically — it is installed via core.hooksPath pointing to .githooks/, which activates on npm install (the prepare script runs git config core.hooksPath .githooks). Merge commits and reverts are exempt. To find or open an issue: gh issue list / gh issue create.
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。