# Cue

> Score and improve AI prompts with feedback, intent-preserving rewrites and Cue account access.

- name: io.github.KingMonkey1/cue
- version: 0.3.7
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 87/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.KingMonkey1%2Fcue
- tools: https://api.protogrid.dev/v1/servers/io.github.KingMonkey1%2Fcue/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "cue": {
      "type": "http",
      "url": "https://cue-mcp-production.up.railway.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 45
- drivers: +website +reachable +uptime-100% +updated-1d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 87/100 (new)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 2 of 2 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: improve_prompt (idempotentHint); get_profile (idempotentHint)
- pass `tools.token_cost`: about 247 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 0 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 247 tokens to load them all
- tool set hash: 4551691f701a559c459a3819c95d943c
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.KingMonkey1/cue.svg)](https://protogrid.dev/servers/io.github.KingMonkey1/cue)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://cue-mcp-production.up.railway.app/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `get_profile`: Always use this tool when the user asks which Cue account is connected, which email is signed in, who they are in Cue, or what Cue plan/subscription/Free/Pro status they have. Returns the authenticated Cue profile and entitlement.
- `improve_prompt`: Always use this tool when the user asks Cue to review, score, refine, rewrite, or improve an AI prompt. Free usage limits and Cue Pro entitlement are enforced by Cue. Returns a 0–10 score, concise feedback, and one improved prompt in the same language as the input.