# PayperDecision

> Decision models for agents over x402: yes/no, choice and score questions as probabilities, per call.

- name: app.payperwork/decisions
- version: 0.4.1
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 90/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/app.payperwork%2Fdecisions
- tools: https://api.protogrid.dev/v1/servers/app.payperwork%2Fdecisions/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "decisions": {
      "type": "http",
      "url": "https://payperwork.app/decide/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-98% +updated-12d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 90/100 (strong)

### 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: 88 (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: models (destructiveHint, idempotentHint, openWorldHint); decide (destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 422 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump
- pass `tools.hidden_text`: no hidden text in tool names, descriptions, schemas or annotations

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name
- pass `stability.new_links`: no tool change named a new site

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

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

- tools: 2, about 422 tokens to load them all
- tool set hash: 97aa0d5ed9fc7d2c7a8bac2d5071b3c2
- badge: [![protogrid quality](https://protogrid.dev/badge/app.payperwork/decisions.svg)](https://protogrid.dev/servers/app.payperwork/decisions)
- 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://payperwork.app/decide/mcp (streamable-http, auth none, reachable true, uptime30d 0.97959185)

## Packages

_none_

## Tools (2)

- `decide`: Answer typed questions about a state with probabilities, in one pass and no generated text. questions is a map of id to {type, instructions, criteria}: noul (yes/no; the answer is the probability of yes), choice (criteria {option_id: description}, 2 to 20; the answer names the option with a probability per option and a confidence), score (criteria [lowest, ..., highest], 2 to 10; the answer is the probability-weighted level, 0 = lowest). Up to 64 questions per call. Models: cloudflare/clef-flash, cloudflare/clef (default cloudflare/clef-flash). Price per decision is quoted in the 402 from your input size (input rate x 1.4 + $0.0005, minimum $0.001); output is free. Charged only if the model call succeeds. The answer is a probability, not a verified fact. Images not accepted yet.
- `models`: List the decision models with rates, the pricing formula, limits and the request and answer shapes. Free.