# Agent Help Network (remote · agenthelpnetwork.com)

Web step blocked? Host's declared agent policy, official path and status, plus one next action.

- Trust score: 80/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `agenthelpnetwork.com`: 80/100 (this document), [markdown](https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork.md), [page](https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork)

## Channel facts

- Endpoint: `https://agenthelpnetwork.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1299 tokens (~433/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 78/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 21% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent Help Network MCP server?

Agent Help Network is a hosted endpoint at https://agenthelpnetwork.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-agenthelpnetwork-agent-help-network 'https://agenthelpnetwork.com/mcp'
```

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.com-agenthelpnetwork-agent-help-network]
url = "https://agenthelpnetwork.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agenthelpnetwork-agent-help-network": {
      "type": "remote",
      "url": "https://agenthelpnetwork.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agenthelpnetwork-agent-help-network --url 'https://agenthelpnetwork.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-agenthelpnetwork-agent-help-network:
    url: "https://agenthelpnetwork.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-agenthelpnetwork-agent-help-network": {
      "Transport": "http",
      "Url": "https://agenthelpnetwork.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agenthelpnetwork-agent-help-network -t streamable-http -u 'https://agenthelpnetwork.com/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-02 (score 80, +1)

- [security] Stability: 0.97 → pass
- [functional improvement] Tool coverage: 15% → 21%
- [cosmetic] “check_incident” added an optional parameter “failed_at”

### 2026-11-01 (score 79, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_incident” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 308 → 411
- [functional improvement] Tool coverage: 10% → 15%
- [functional] New tool “rate_last_lookup”

### 2026-10-30 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 75, +7)

- [security improvement] Authorization: fail → partial
- [security] Tool “check_incident” rewrote its description, which is the text the model reads
- [security] Tool “report_observation” no longer declares itself destructive
- [functional regression] Schema quality: 206 → 308
- [functional regression] Schema quality: 206 → 258
- [functional improvement] Tool coverage: 0% → 10%
- [functional improvement] Tool coverage: 0% → 11%
- [cosmetic] “check_incident” added an optional parameter “agent_vendor”
- [cosmetic] “check_incident” added an optional parameter “challenge”
- [cosmetic] “check_incident” added an optional parameter “http_status”
- [cosmetic] “check_incident” added an optional parameter “retry_after”
- [cosmetic] “check_incident” added an optional parameter “via”

### 2026-10-20 (score 68, 0)

- [security] Tool “check_incident” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 185 → 206

## MCP tools (3)

### `check_incident` (~637 tokens)

Call this when a web step is blocked or failing for no clear reason (a 403 or access denied, a 429, a 5xx or a timeout, a login wall, a "verify you are human" or CAPTCHA page), or when asked "is this site down?" or whether its robots rules block agents. Skip it when the page opened normally or your own tool or platform already said why it refused (e.g. robots.txt or policy). Look the host up once per blocked step, before deciding whether to retry. Send the public hostname, never a URL path, query or credentials; add codes only when you observed them: error_class (site_access, login_auth, human_verification, service_error), failure_stage (before_target_response, response_observed, access_denial_observed, unknown), http_status, challenge, retry_after, via. Send agent_vendor only when you know which vendor's documented robots.txt token your requests send: openai, anthropic (Claude-User), google, perplexity, meta, mistral, amazon, microsoft, apple, duckduckgo, diffbot, exa, or other if none. Browser automation usually sends a normal browser user agent, so robots.txt agent tokens may not apply; leave agent_vendor out then, and whenever unsure. It selects robots.txt groups (not stored). The answer: summary_line, next_action (do, url, retry_after_seconds), recommendation.action, access_profile (declared policy), official_paths, provider_status and observations. A no_reports result means no observations, not a healthy site. Then follow next_action: it may say to continue, wait for the provider, use a listed official path, hand the step to the user, stop retrying, or look up once more. On 'pending', look up once more after retry_after_seconds; do not poll. Read-only: it may fetch the host's public robots.txt, llms.txt and status feed, and the home page unless robots.txt bars it (ahn_check), never changes the target site or your data; lookups and the codes you send are counted anonymously per host and hour. The first text block is a one-line summary; next_action gives the st…

Input parameters:

- `agent_vendor` (string)
- `challenge` (string)
- `error_class` (string)
- `failed_at` (string): When the step failed, as an ISO 8601 time such as 2026-11-01T07:10:00Z (UTC if no offset). Leave it out for a failure that just happened. Only used to choose the cause shown in the answer; not stored.
- `failure_stage` (string)
- `http_status` (integer): HTTP status the site returned: 401, 402, 403, 407, 408, 429, 451 or 500-599. Leave out if unknown.
- `retry_after` (string)
- `site_host` (string, required)
- `task_step` (string)
- `via` (string)

Output parameters:

- `access_profile`
- `ahn_check`
- `cause`
- `current_site_status` (string)
- `data_horizon_hours` (integer)
- `evidence_level` (string)
- `failure_stage`
- `failures` (integer)
- `feedback_token`
- `generated_at` (string)
- `host_facts`
- `links`
- `lookup_activity`
- `next_action`
- `next_checks` (array)
- `observations` (array)
- `official_paths`
- `official_status_page`
- `provider_discovery_attempted_at`
- `provider_source_state` (string)
- `provider_status`
- `recommendation`
- `reporting_sources` (integer)
- `site_host` (string)
- `successes` (integer)
- `summary` (string)
- `summary_code` (string)
- `summary_line`
- `synthetic` (boolean)
- `window_hours` (integer)

### `rate_last_lookup` (~174 tokens)

If an earlier check_incident answer gave you a feedback token and you then tried again, say whether it worked. Sends only the token and the outcome code, no hostname. outcome: succeeded (the next attempt worked), still_blocked, handed_off (you handed the step to the user) or gave_up. path: official_path (you used the official path the answer pointed to), same_site (you retried the same site) or unknown. A token works once and expires one hour after the lookup; do not send one for an attempt you did not make. The outcome is counted anonymously per host and hour and does not change any answer.

Input parameters:

- `outcome` (string, required)
- `path` (string)
- `token` (string, required): The feedback_token.token value from the check_incident answer, unchanged.

Output parameters:

- `accepted` (boolean)

### `report_observation` (~59 tokens)

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.

Input parameters:

- `observation` (required)

Output parameters:

- `incident_id` (string)
- `observation_id` (string)
- `review_state` (string)
- `synthetic` (boolean)
- `withdrawal_token`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork#diagnostics

## Score history

- 2026-11-04: 80
- 2026-11-03: 80
- 2026-11-02: 80
- 2026-11-01: 79
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 78
- 2026-10-28: 78
- 2026-10-27: 77
- 2026-10-26: 77
- 2026-10-25: 76
- 2026-10-24: 76
- 2026-10-23: 76
- 2026-10-22: 75
- 2026-10-21: 68
- 2026-10-20: 68
- 2026-10-19: 68
- 2026-10-18: 68
- 2026-10-17: 67
- 2026-10-16: 66
- 2026-10-15: 66
- 2026-10-14: 65
- 2026-10-13: 65
- 2026-10-12: 64
- 2026-10-10: 63
- 2026-10-09: 63
- 2026-10-08: 63
- 2026-10-06: 62
- 2026-10-04: 61
- 2026-10-03: 61

## Common questions

### What is the Agent Help Network MCP server?

Agent Help Network is an MCP server listed in the public MCP registry as com.agenthelpnetwork/agent-help-network. Web step blocked? Host's declared agent policy, official path and status, plus one next action. This page covers its hosted endpoint (https://agenthelpnetwork.com/mcp).

### Is the Agent Help Network MCP server safe to use?

Agent Help Network scores 80 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Help Network MCP server expose?

Agent Help Network exposes 3 tools: check_incident, rate_last_lookup, report_observation. Their descriptions and schemas cost roughly 870 tokens of context every time the server is loaded.

### Does the Agent Help Network MCP server require authentication?

No. We connected to Agent Help Network without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Help Network MCP server still maintained?

Agent Help Network is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agenthelpnetwork.com/mcp
- Repository: https://github.com/agent-help-network/agent-help-network
- Website: https://agenthelpnetwork.com/en/
- Changelog RSS feed: https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork.json
- HTML version of this page: https://verifymcp.io/servers/com-agenthelpnetwork-agent-help-network/agenthelpnetwork