Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Rebuilds the scores real systems run on you — credit, actuarial, lending — in the open, cited.
Facts
- MCP registry
com.lifescored/mcp· 1.0.0- Endpoint
https://lifescored.com/mcp- Website
- lifescored.com
- GitHub stars
- 1
- Registry entry
- updated 17 Jun 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under lifescored.com, a namespace the registry only gives to whoever proves they control that domain.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 4 · about 357 tokens of context · checked 13 minutes ago
| Tool | What it does | Hint |
|---|---|---|
get_rulebookGet the full rulebook + math | The complete life-score rulebook and exact math: every rule (weight, bounds, evidence, source, formula), the input schema (what to ask the user), and the engine constants. Use this to compute a score on your OWN side —… | |
get_input_schemaGet the questions to ask | Just the fields to collect from the user, with types, ranges/allowed values, defaults, and plain-language help. Ask only for what you do not already know; missing fields fall back to their default. | |
get_methodologyHow the scoring works | Plain-English explanation of how scoring works, the two governing principles, what is deliberately left out (protected characteristics, luck), and the privacy stance. Use to answer "how does this work / is this fair"… | |
how_to_give_feedbackHow to propose an improvement | How to suggest a better weight, a fresh source, or a new rule via GitHub, so improvements from many people aggregate in the open. |
What https://lifescored.com/mcp answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 0 errors · 4 warnings · 1 note
- warnTC16get_input_schemano readOnlyHint or destructiveHint
- warnTC16get_methodologyno readOnlyHint or destructiveHint
- warnTC16get_rulebookno readOnlyHint or destructiveHint
- warnTC16how_to_give_feedbackno readOnlyHint or destructiveHint
- noteTC24server4 of 4 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 357 tokens of definitions. Not part of the score yet. Check your own server.