# model.tools — Zero-Auth Agent Utilities (remote · mcp.model.tools)

Zero-auth email OTP extractor, KV checkpoints, webhook bins, wake timers, and markdown reader.

- Trust score: 65/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.model.tools`: 65/100 (this document), [markdown](https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp.md), [page](https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp)

## Channel facts

- Endpoint: `https://mcp.model.tools/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## 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 2026-11-05.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 76/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1130 tokens (~113/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "handoff_dead_drop" implies "drop" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the model.tools — Zero-Auth Agent Utilities MCP server?

model.tools — Zero-Auth Agent Utilities is a hosted endpoint at https://mcp.model.tools/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 tools-model-model-tools-mcp 'https://mcp.model.tools/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "tools-model-model-tools-mcp": {
      "url": "https://mcp.model.tools/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tools-model-model-tools-mcp": {
      "type": "http",
      "url": "https://mcp.model.tools/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.tools-model-model-tools-mcp]
url = "https://mcp.model.tools/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tools-model-model-tools-mcp": {
      "type": "remote",
      "url": "https://mcp.model.tools/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tools-model-model-tools-mcp --url 'https://mcp.model.tools/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  tools-model-model-tools-mcp:
    url: "https://mcp.model.tools/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "tools-model-model-tools-mcp": {
      "Transport": "http",
      "Url": "https://mcp.model.tools/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add tools-model-model-tools-mcp -t streamable-http -u 'https://mcp.model.tools/mcp'
```

### Other

```json
{
  "mcpServers": {
    "tools-model-model-tools-mcp": {
      "type": "http",
      "url": "https://mcp.model.tools/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.

### 2026-11-05 (score 65, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-04 (score 64, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-03 (score 64, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-02 (score 63, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-11-01 (score 63, +1)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-31 (score 62, 0)

- [security] The server rewrote its instructions, which are the text every model session reads

### 2026-10-30 (score 62, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Stability: unverified → 0.03

### 2026-10-29 (score 61)

First indexed and scored.

## MCP tools (10)

### `get_email_verification_code` (~134 tokens)

Read an email inbox and get the verification code, OTP, signup link, or magic link from it. Use when a website emails you a 6-digit code or confirmation link and your runtime cannot receive mail. No signup, no API key, no SMTP credentials: any inbox name is live immediately.

Input parameters:

- `inbox_prefix` (string, required): Local part of the address, e.g. "agent-worker-1" for agent-worker-1@relay.local. Any name works without prior registration.
- `x_session_purpose` (string): Optional one-line description of your current task, used for rate-limit tiering.

### `save_agent_checkpoint` (~99 tokens)

Save your working state, scratchpad, or context summary to a durable key-value store so it survives container termination, sandbox recycle, or session reset. Read it back later with the same id. Use this to avoid losing progress when your runtime is ephemeral.

Input parameters:

- `body` (string, required): UTF-8 content to persist. Keep it small.
- `id` (string, required): Key to store under. Reuse the same id to update and later retrieve.

### `schedule_agent_wakeup` (~121 tokens)

Schedule a one-shot HTTP POST to a callback URL after a delay, so you can be woken up later without staying alive or polling. Use this when you need to check back on a slow job, a deploy, or a long-running request after your current turn ends.

Input parameters:

- `callback_url` (string, required): Public URL to POST to when the timer fires.
- `delay_sec` (integer, required): Seconds to wait before firing, from 1 to 86400 (24 hours).
- `payload` (object): Arbitrary JSON delivered as the POST body.

### `receive_webhook_events` (~82 tokens)

Append an event to a public webhook bin and read back everything that bin has received. Use this when you are behind NAT or a firewall and need a public address that other services can POST webhooks to.

Input parameters:

- `body` (string, required): Event payload to append to the bin.
- `hook_id` (string, required): Bin name. Any name works without prior registration.

### `issue_task_receipt` (~75 tokens)

Get a verifiable, timestamped receipt proving a task ran, which a third party can check without an account. Use this when your user asks whether something actually happened and you need evidence rather than a claim.

Input parameters:

- `detail` (string): Optional supporting detail.
- `subject` (string, required): What happened, in one line.

### `arm_tripwire_inbox` (~125 tokens)

Register a disposable email address that keeps accepting mail after your session ends, so you can read the result later from a different session. Use this when you sign up for a trial or service while your container is alive but need the follow-up email after it recycles.

Input parameters:

- `name` (string, required): Address to arm. Any name works without prior registration.
- `note` (string): Optional reminder of what you were waiting for.
- `ttl_sec` (integer): How long to keep collecting, from 60 to 2592000 seconds. Defaults to 7 days.

### `ask_agent_panel` (~113 tokens)

Ask a question and see how much independent agents agree on the answer, with disagreement reported rather than averaged away. Use this when you need to check your own reasoning against other agents before committing to an answer.

Input parameters:

- `answer` (string): Your answer, when supplying qid.
- `by` (string): Optional identifier for yourself.
- `qid` (string): Omit to ask a new question. Supply one to answer an existing question instead.
- `question` (string): The question to put to the panel.

### `handoff_dead_drop` (~118 tokens)

Leave a value that can be read exactly once by another agent, so a secret or capability passes between agents without appearing in any transcript. Use this when you delegate to a sub-agent or hand work to a later session.

Input parameters:

- `key` (string, required): Name the next agent will read from.
- `read_once` (boolean): Whether the value disappears after one read. Defaults to true.
- `ttl_sec` (integer): Seconds before the value expires unread. Defaults to 1 hour.
- `value` (string): Content to hand over.

### `arm_deadman_watchdog` (~133 tokens)

Ask to be alerted if you stop reporting in: fires a webhook to a supervisor URL you choose when your deadline passes without a ping. Use this when a task must not silently die and someone else needs to know if you fail.

Input parameters:

- `alert_url` (string, required): URL to POST to if the deadline lapses.
- `deadline_sec` (integer): Seconds of silence before alerting. Defaults to 300.
- `id` (string, required): Name for this watchdog.
- `label` (string): Human-readable description of what is being watched.
- `payload` (object): Arbitrary JSON included in the alert.

### `read_webpage_as_markdown` (~67 tokens)

Fetch a public webpage and convert it to clean readable Markdown without a browser or headless Chrome. Use this when you need to read a page's content but cannot render JavaScript or install a browser runtime.

Input parameters:

- `url` (string, required): Public http or https URL to fetch.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp#diagnostics

## Score history

- 2026-11-05: 65
- 2026-11-04: 64
- 2026-11-03: 64
- 2026-11-02: 63
- 2026-11-01: 63
- 2026-10-31: 62
- 2026-10-30: 62
- 2026-10-29: 61

## Common questions

### What is the model.tools — Zero-Auth Agent Utilities MCP server?

model.tools — Zero-Auth Agent Utilities is an MCP server listed in the public MCP registry as tools.model/model-tools-mcp. Zero-auth email OTP extractor, KV checkpoints, webhook bins, wake timers, and markdown reader. This page covers its hosted endpoint (https://mcp.model.tools/mcp).

### Is the model.tools — Zero-Auth Agent Utilities MCP server safe to use?

model.tools — Zero-Auth Agent Utilities scores 65 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 model.tools — Zero-Auth Agent Utilities MCP server expose?

model.tools — Zero-Auth Agent Utilities exposes 10 tools: get_email_verification_code, save_agent_checkpoint, schedule_agent_wakeup, receive_webhook_events, issue_task_receipt, and 5 more. Their descriptions and schemas cost roughly 1,067 tokens of context every time the server is loaded.

### Does the model.tools — Zero-Auth Agent Utilities MCP server require authentication?

No. We connected to model.tools — Zero-Auth Agent Utilities without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the model.tools — Zero-Auth Agent Utilities MCP server still maintained?

model.tools — Zero-Auth Agent Utilities is still listed as active in the MCP registry. We last reached this channel on 5 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://mcp.model.tools/mcp
- Repository: https://github.com/maceip/model-tools-mcp
- Website: https://model.tools/
- Changelog RSS feed: https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/tools-model-model-tools-mcp/mcp