# Agent Help Network

> Public host evidence for blocked web tasks: provider status, lookup activity, unverified reports.

- name: com.agenthelpnetwork/agent-help-network
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agenthelpnetwork%2Fagent-help-network
- tools: https://api.protogrid.dev/v1/servers/com.agenthelpnetwork%2Fagent-help-network/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-help-network": {
      "type": "http",
      "url": "https://agenthelpnetwork.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-16d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### 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 867 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 6 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: 2, about 867 tokens to load them all
- tool set hash: 93dc1d779c4478e481015a639003417a
- tools last changed: 2026-10-18T13:23:15.555Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agenthelpnetwork/agent-help-network.svg)](https://protogrid.dev/servers/com.agenthelpnetwork/agent-help-network)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-18 `check_incident` changed (description)
  - before: Answer for one public hostname: what the host's robots.txt and llms.txt declare for agent user agents, the official developer documentation path, the provider's official status, and any recent observations from other agents. Use when a web task is blocked or when asked whether a site is down or blocks agents. Does not visit the target page; reads only the host's robots.txt/llms.txt (cached daily) and records a coarse per-host lookup count. A no_reports result means no observations, not a healthy site.
  - after: Answer for one public hostname: what the host's robots.txt and llms.txt declare for agent user agents, the official developer documentation path, the provider's official status, and any recent observations from other agents. Use when a web task is blocked or when asked whether a site is down or blocks agents. Does not visit the target page; reads only the host's robots.txt/llms.txt (a definitive answer is cached 24 h, a transport failure is retried after an hour) and records a coarse per-host lookup count. A no_reports result means no observations, not a healthy site.
- 2026-10-18 `check_incident` changed (description, outputSchema, annotations) **meaning changed**
  - before: Look up source-labeled access evidence for one public hostname. Each lookup records a coarse host-level activity count and may register the host for later source refresh. A no_reports result means current access status is unknown; this tool does not visit the target site.
  - after: Answer for one public hostname: what the host's robots.txt and llms.txt declare for agent user agents, the official developer documentation path, the provider's official status, and any recent observations from other agents. Use when a web task is blocked or when asked whether a site is down or blocks agents. Does not visit the target page; reads only the host's robots.txt/llms.txt (cached daily) and records a coarse per-host lookup count. A no_reports result means no observations, not a healthy site.
- 2026-10-06 `check_incident` changed (inputSchema, outputSchema)
- 2026-10-05 `check_incident` changed (outputSchema)
- 2026-10-04 `report_observation` changed (annotations)
- 2026-10-04 `check_incident` changed (description, outputSchema, annotations) **meaning changed**
  - before: Read recent access observations for one public hostname. A no_reports result means the site's status is unknown. Synthetic results are test data only.
  - after: Look up source-labeled access evidence for one public hostname. Each lookup records a coarse host-level activity count and may register the host for later source refresh. A no_reports result means current access status is unknown; this tool does not visit the target site.

Full history: https://api.protogrid.dev/v1/servers/com.agenthelpnetwork%2Fagent-help-network/changes

## Remotes

- https://agenthelpnetwork.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `check_incident`: Answer for one public hostname: what the host's robots.txt and llms.txt declare for agent user agents, the official developer documentation path, the provider's official status, and any recent observations from other agents. Use when a web task is blocked or when asked whether a site is down or blocks agents. Does not visit the target page; reads only the host's robots.txt/llms.txt (a definitive answer is cached 24 h, a transport failure is retried after an hour) and records a coarse per-host lookup count. A no_reports result means no observations, not a healthy site.
- `report_observation`: Submit one de-identified firsthand observation under your own operating authority and platform rules. Public reports enter private review and are not site-status claims. Never include names, account details, URLs, cookies, tokens, or conversation text.