# HumanMirror One

> Agent routing, safety preflight, execution receipts, best execution and verified outcomes.

- name: fr.humanmirror/one
- version: 1.0.3
- connection class: R0 (autonomous)
- trust: 92/100 flags: duplicate-repo
- quality: 77/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/fr.humanmirror%2Fone
- tools: https://api.protogrid.dev/v1/servers/fr.humanmirror%2Fone/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "one": {
      "type": "http",
      "url": "https://humanmirror.fr/api/one/mcp/",
      "headers": {
        "Authorization": "Bearer ${ONE_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${ONE_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-99% +updated-10d-ago -duplicate-repo(8 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 77/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### 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: 71 (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
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: humanmirror_do (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 435 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 50 (weight 15)

- pass `stability.changes`: 2 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 1, about 435 tokens to load them all
- tool set hash: f61c5b4912d8489e4236153db2fd00a0
- tools last changed: 2026-10-11T11:42:53.978Z
- badge: [![protogrid quality](https://protogrid.dev/badge/fr.humanmirror/one.svg)](https://protogrid.dev/servers/fr.humanmirror/one)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-11 `humanmirror_do` changed (description) **meaning changed**
  - before: One HumanMirror tool for verified outcomes and canonical intent routing. Provide intent to route free to the correct HumanMirror safety, commerce, payment or best-execution boundary. Provide outcome_type/input for a directly verified Outcome; 6 Nexus credits are kept only on verified success.
  - after: HumanMirror Agent Control Plane in one MCP tool. Use free intent routing to resolve the right capability, pre-execution safety boundary or post-execution evidence path before spending anything. For measurable deterministic work, outcome_type/input can run a verified Outcome; 6 Nexus credits are kept only on verified success.
- 2026-09-27 `humanmirror_do` changed (description, inputSchema) **meaning changed**
  - before: One HumanMirror tool for measurable deterministic outcomes. Set dry_run=true for a free quote. Otherwise HumanMirror executes and independently verifies the result; 6 Nexus credits are kept only on verified success and refunded on execution or verification failure.
  - after: One HumanMirror tool for verified outcomes and canonical intent routing. Provide intent to route free to the correct HumanMirror safety, commerce, payment or best-execution boundary. Provide outcome_type/input for a directly verified Outcome; 6 Nexus credits are kept only on verified success.

Full history: https://api.protogrid.dev/v1/servers/fr.humanmirror%2Fone/changes

## Remotes

- https://humanmirror.fr/api/one/mcp/ (streamable-http, auth none, reachable true, uptime30d 0.9915254)

## Packages

_none_

## Tools (1)

- `humanmirror_do`: HumanMirror Agent Control Plane in one MCP tool. Use free intent routing to resolve the right capability, pre-execution safety boundary or post-execution evidence path before spending anything. For measurable deterministic work, outcome_type/input can run a verified Outcome; 6 Nexus credits are kept only on verified success.