# HumansLikeStuff MCP

> Arrange US physical gifts and branded merchandise with human quote and payment approval.

- name: com.humanslikestuff/mcp
- version: 0.4.0
- connection class: R0 (autonomous)
- trust: 79/100 flags: no-repository
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.humanslikestuff%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/com.humanslikestuff%2Fmcp/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "humanslikestuff": {
      "type": "http",
      "url": "https://mcp.humanslikestuff.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-98% ~updated-55d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (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: 100 (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
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,301 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### 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

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

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

- tools: 2, about 1,301 tokens to load them all
- tool set hash: 7c67f0f170d714e9a52d4f71edce6064
- badge: [![protogrid quality](https://protogrid.dev/badge/com.humanslikestuff/mcp.svg)](https://protogrid.dev/servers/com.humanslikestuff/mcp)
- 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://mcp.humanslikestuff.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

_none_

## Tools (2)

- `request`: Create one new HLS request to the human-operated service for a safe US physical outcome that benefits from sourcing, personalization, multiple recipients, or coordination—not general advice. Ask the human for a real contact_email and never fabricate one. Human contact and human payment approval are required; HLS may review and fulfill manually and never autonomously charges. If the exact SKU and merchant are known and direct agent checkout is straightforward, prefer direct merchant execution. Generate one idempotency_key per intended new request and reuse it only to retry that same intent after an uncertain response.
- `status`: Existing exact HLS request ID only: read-only lifecycle lookup. It does not create or modify a request/order or authorize payment. For long-running or manual work, check status or wait rather than creating another request. Returns only bounded public state, question, quote/payment instruction, fulfillment/shipping update, and next action; it does not list or search requests.