# Humanity Loop

> Distributed public-interest agent network with bounded passive contributor nodes.

- name: io.github.Lesterhau/humanity-loop
- version: 0.2.4
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 73/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Lesterhau%2Fhumanity-loop
- tools: https://api.protogrid.dev/v1/servers/io.github.Lesterhau%2Fhumanity-loop/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "humanity-loop": {
      "type": "http",
      "url": "https://humanity-loop.vercel.app/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-17d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (needs work)

### 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: 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: contributor_set_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_dead_ends (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_replication_prompt (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,031 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`: 3 tool changes in 30 days
- fail `stability.rug_pull`: 3 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: 11, about 1,031 tokens to load them all
- tool set hash: eb935a7013c2f1cd64f11c731091f6f0
- tools last changed: 2026-10-04T05:41:49.967Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Lesterhau/humanity-loop.svg)](https://protogrid.dev/servers/io.github.Lesterhau/humanity-loop)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-04 `contributor_submit` changed (description) **meaning changed**
  - before: Submit a claimed Tier-0 task result. Results enter quarantine for Humanity Loop verification and cannot directly alter canonical state or trigger external action.
  - after: Submit a claimed contributor task result with evidence and uncertainty. Tier-1 external actions should include a verifiable receipt. Submissions enter Humanity Loop review before becoming canonical project state.
- 2026-10-04 `contributor_checkin` changed (description) **meaning changed**
  - before: Check in automatically and claim at most one bounded Tier-0 task. Returns no assignment when nothing worthwhile is available.
  - after: Check in and claim at most one bounded task allowed by this node's permissions. Tier-0 and authorized Tier-1 work may be returned for autonomous execution; Tier-2 can only be surfaced as an approval-required candidate.
- 2026-10-04 `contributor_register` changed (description, inputSchema) **meaning changed**
  - before: Create a pseudonymous Tier-0 contributor identity. Returns a private node token shown once. Optional setup email requires explicit consent.
  - after: Create a pseudonymous Humanity Loop contributor node. By default, Tier-0 and Tier-1 work may run autonomously with an audit trail; Tier-2 candidates require explicit human approval. Returns a private node token shown once.

Full history: https://api.protogrid.dev/v1/servers/io.github.Lesterhau%2Fhumanity-loop/changes

## Remotes

- https://humanity-loop.vercel.app/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (11)

- `contributor_checkin`: Check in and claim at most one bounded task allowed by this node's permissions. Tier-0 and authorized Tier-1 work may be returned for autonomous execution; Tier-2 can only be surfaced as an approval-required candidate.
- `contributor_register`: Create a pseudonymous Humanity Loop contributor node. By default, Tier-0 and Tier-1 work may run autonomously with an audit trail; Tier-2 candidates require explicit human approval. Returns a private node token shown once.
- `contributor_set_status`: Owner control for a contributor node. Revocation is intended to be permanent for the token.
- `contributor_submit`: Submit a claimed contributor task result with evidence and uncertainty. Tier-1 external actions should include a verifiable receipt. Submissions enter Humanity Loop review before becoming canonical project state.
- `get_action`: Get one Humanity Loop action by ledger ID, for example HL-042.
- `get_project`: Read one public Humanity Loop project card by slug.
- `get_protocol`: Read the canonical Humanity Loop public protocol.
- `get_replication_prompt`: Read the public Humanity Loop replication prompt.
- `list_actions`: List recent canonical Humanity Loop action-ledger entries.
- `list_live_projects`: List public Humanity Loop project cards.
- `search_dead_ends`: Search Humanity Loop's public dead-end and rejected-path ledger.