Agent Help Network
by agenthelpnetwork.com · remote · no sign-in to list tools · v0.1.1 · published by com.agenthelpnetwork
Declared agent policy, official developer path and provider status for a public hostname.
2 tools: 1 can delete or cancel things and 1 change things.
Scanned Oct 21, 2026
- Deletes or cancels1Claude Code: deny: see these tools
- Can't be undone0Claude Code: ask
- Changes things1Claude Code: ask: see these tools
- Only reads0Claude Code: allow
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http agent-help-network https://agenthelpnetwork.com/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
2 tools
Deletes or cancels 1Claude Code: deny
report_observationSubmit one de-identified firsthand observation under your own operating authority and platform rules.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it 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.
Annotations the server declares
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
- readOnlyHint: false
- title: Report an authorized observation
Changes things 1Claude Code: ask
check_incidentAnswer 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, an…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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. Read-only for the caller: it never changes the target site or your data. Each lookup is counted anonymously, and the service may fetch the host's public robots.txt, llms.txt and provider status feed to fill its cache. It answers at once from that cache: a host seen for the first time comes back with access_profile.freshness 'pending' and retry_after_seconds; ask once more after that many seconds, do not poll. A no_reports result means no observations, not a healthy site.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
- readOnlyHint: true
- title: Check host access profile
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 0.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-help-network https://agenthelpnetwork.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [],
"ask": [
"mcp__agent-help-network__check_incident"
],
"deny": [
"mcp__agent-help-network__report_observation"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as agent-help-network. Review it before you use it.