# Agent Toolbox (remote · agent-toolbox.zafermemon87.workers.dev)

Everyday tools for AI agents, paid per call with x402: images, markdown, speech-to-text, embeddings.

- Trust score: 63/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

> **Recent critical change**: Authorization (2026-10-26). See the changelog below before you install this server.

## Components

- remote · `agent-toolbox.zafermemon87.workers.dev`: 63/100 (this document), [markdown](https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox.md), [page](https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox)

## Channel facts

- Endpoint: `https://agent-toolbox.zafermemon87.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-11-04.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (stop_watch).
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - 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**: 66/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3250 tokens (~135/item across 24 items; 24 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Agent Toolbox MCP server?

Agent Toolbox is a hosted endpoint at https://agent-toolbox.zafermemon87.workers.dev/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 zaffy18-agent-toolbox 'https://agent-toolbox.zafermemon87.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "zaffy18-agent-toolbox": {
      "url": "https://agent-toolbox.zafermemon87.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "zaffy18-agent-toolbox": {
      "type": "http",
      "url": "https://agent-toolbox.zafermemon87.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.zaffy18-agent-toolbox]
url = "https://agent-toolbox.zafermemon87.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zaffy18-agent-toolbox": {
      "type": "remote",
      "url": "https://agent-toolbox.zafermemon87.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add zaffy18-agent-toolbox --url 'https://agent-toolbox.zafermemon87.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  zaffy18-agent-toolbox:
    url: "https://agent-toolbox.zafermemon87.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "zaffy18-agent-toolbox": {
      "Transport": "http",
      "Url": "https://agent-toolbox.zafermemon87.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add zaffy18-agent-toolbox -t streamable-http -u 'https://agent-toolbox.zafermemon87.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "zaffy18-agent-toolbox": {
      "type": "http",
      "url": "https://agent-toolbox.zafermemon87.workers.dev/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.

### 2026-11-04 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 60, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “url_to_markdown” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2849 → 3250
- [functional] New tool “extract_free”
- [functional] New tool “screenshot”
- [cosmetic] “extract_data” added an optional parameter “render”
- [cosmetic] “url_to_markdown” added an optional parameter “render”

### 2026-10-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 59, −6)

- [critical regression] Authorization: partial → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] New tool “stop_watch”, which the server declares destructive
- [functional regression] Schema quality: 2172 → 2849
- [functional] New tool “extract_data”
- [functional] New tool “watch_field”
- [functional] New tool “watch_status”

### 2026-10-25 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 1761 → 2172
- [functional improvement] Stability: unverified → 0.03
- [functional] New tool “company_lei”
- [functional] New tool “company_search”
- [functional] New tool “company_us”

### 2026-10-24 (score 65)

First indexed and scored.

## MCP tools (24)

### `generate_image` (~125 tokens)

Generate Image

Generate a 1024x1024 JPEG image from a text prompt with FLUX.1 schnell; every prompt passes a safety check first (sexual content and other unsafe requests are refused and not charged). Returns the image as base64. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `prompt` (string, required): What to draw, up to 2048 characters
- `steps` (integer): Diffusion steps, 1 to 8 (default 4; more is slower and finer)

### `url_to_markdown` (~142 tokens)

Url To Markdown

Fetch a public web page or document (HTML, PDF, Word, Excel, CSV, XML; up to 10 MB) and return it as clean Markdown with its title and final URL. Add render=true for pages that build their content with JavaScript: they are opened in a real headless Chrome first. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `render` (boolean): Open the page in a real headless Chrome first, for pages built with JavaScript (slower; default false)
- `url` (string, required): A public http(s) URL

### `file_to_markdown` (~98 tokens)

File To Markdown

Convert an uploaded document (PDF, Word, Excel, CSV, HTML, XML, OpenDocument; up to 10 MB) to Markdown. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `file_base64` (string, required): The file, base64-encoded
- `filename` (string, required): File name with extension, e.g. report.pdf

### `transcribe_audio` (~162 tokens)

Transcribe Audio

Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `audio_base64` (string): The audio file, base64-encoded
- `audio_url` (string): A public http(s) URL
- `language` (string): Language code such as en or hi (detected when left out)
- `task` (string): translate = into English

### `embed_text` (~85 tokens)

Embed Text

Text embeddings with BGE-M3 (multilingual, 1024 dimensions) for search, clustering and RAG: up to 100 texts of up to 8,000 characters per call. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `texts` (array, required): Texts to embed

### `translate_text` (~96 tokens)

Translate Text

Translate text (up to 5,000 characters) between 100 languages with M2M100 1.2B. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `source_lang` (string): Default english
- `target_lang` (string, required): Language name or code, e.g. french or fr
- `text` (string, required)

### `summarize` (~117 tokens)

Summarize

Summarize text (up to 60,000 characters) or a public web page or PDF by URL with Llama 3.1 8B, short, medium or long, optionally focused on a topic. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `focus` (string): Optional topic to focus on
- `length` (string)
- `text` (string)
- `url` (string): A public http(s) URL

### `verify_email` (~85 tokens)

Verify Email

Check an email address: format, whether the domain exists and accepts mail (MX records), disposable providers, role accounts and free providers, with a valid / risky / invalid verdict. The mailbox itself is not probed. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `email` (string, required)

### `fx_rates` (~120 tokens)

Fx Rates

Currency exchange rates and conversion for about 30 currencies (USD, EUR, GBP, INR, JPY, CNY ...) from the European Central Bank reference rates of the latest working day. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `amount` (number): Amount to convert (default 1)
- `base` (string): Base currency, default USD
- `symbols` (string): Comma-separated, e.g. EUR,INR (default: all)

### `dns_lookup` (~101 tokens)

Dns Lookup

DNS records of a domain (A, AAAA, MX, TXT, NS, CNAME, SOA, CAA, SRV, PTR) over DNS-over-HTTPS (1.1.1.1), with DNSSEC validation status. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `name` (string, required): Domain name
- `type` (string)

### `chat_gpt_oss_120b` (~183 tokens)

Chat Gpt Oss 120b

OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `max_tokens` (integer): Default 2048
- `messages` (array, required): OpenAI chat messages: [{role: system|user|assistant, content}] (up to 32,000 characters in total)
- `response_format` (object): {"type": "json_object"} for JSON output
- `temperature` (number)

### `chat_qwen3_30b` (~179 tokens)

Chat Qwen3 30b

OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `max_tokens` (integer): Default 2048
- `messages` (array, required): OpenAI chat messages: [{role: system|user|assistant, content}] (up to 32,000 characters in total)
- `response_format` (object): {"type": "json_object"} for JSON output
- `temperature` (number)

### `domain_whois` (~74 tokens)

Domain Whois

Domain registration data from RDAP (the successor of WHOIS): registrar, creation, expiry and update dates, status codes, nameservers and DNSSEC. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `domain` (string, required)

### `company_search` (~137 tokens)

Company Search

Find companies worldwide by name in the official GLEIF register of legal entities: legal name, LEI, country, registered address, company-register number, legal form and status, best match first, plus matching US-listed companies with ticker and SEC CIK. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `country` (string): Optional two-letter country code to narrow the search, e.g. IN
- `limit` (integer): How many matches (default 5)
- `query` (string, required): Company name, e.g. Reliance Industries

### `company_lei` (~119 tokens)

Company Lei

Full official record of a legal entity by its LEI (Legal Entity Identifier) from GLEIF: legal and other names, registered and head-office addresses, company-register number, legal form, status, founding date, LEI status, and its direct and ultimate parent companies. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `lei` (string, required): 20-character LEI, e.g. HWUPKR0MPOU8FGXBT394

### `company_us` (~145 tokens)

Company Us

US public company profile from SEC EDGAR by ticker or CIK: industry, exchange, state of incorporation, fiscal year end, address and phone, shares outstanding, latest full-year financials (revenue, net income, assets, liabilities, equity, cash, diluted EPS) and links to the latest 10-K, 10-Q and 8-K filings. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `cik` (string): SEC CIK number, e.g. 320193 (instead of ticker)
- `ticker` (string): Stock ticker, e.g. AAPL

### `extract_data` (~225 tokens)

Extract Data

Extract structured JSON from a web page, PDF or text: name the fields you want (up to 25, with types) and get each value with the exact quote from the page that states it. Every quote is checked against the page itself (verified, quoted, unverified or not_found), so values are never invented. Charged only when at least one field is found. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `fields` (object, required): Field name -> "type: what it is" (types: string, number, integer, boolean), e.g. {"price": "number: the current price"}; a JSON Schema with properties also works
- `render` (boolean): Open the page in a real headless Chrome first, for pages built with JavaScript (slower; default false)
- `text` (string): Text to read instead of a URL (up to 60,000 characters)
- `url` (string): A public http(s) URL

### `screenshot` (~126 tokens)

Screenshot

Screenshot of a public web page in a real headless Chrome after it has loaded (JavaScript included): a JPEG of the visible window or the full page, 320 to 1920 pixels wide, as base64. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `full_page` (boolean): The whole page instead of the first screen (default false)
- `url` (string, required): A public http(s) URL
- `width` (integer): Window width in pixels (default 1280)

### `watch_field` (~342 tokens)

Watch Field

Watch one field on a web page for 30 days, e.g. a price, stock status or version number: it is read again every 15 to 1440 minutes and an alert goes to your webhook, Slack, Discord or Telegram when it changes, goes below or above a number, contains a text, or disappears. Returns the current value now; check status or stop it for free with the watch secret. Costs USD 0.10 per call, paid with x402 (USDC on Base); calls that fail are not charged.

Input parameters:

- `callback_url` (string): Optional https URL for alerts (a signed JSON POST); Slack and Discord incoming webhooks and https://api.telegram.org/bot<token>/sendMessage?chat_id=<id> get a readable message. Without it, poll the s…
- `description` (string): What the field is, e.g. the current price of the product
- `every_minutes` (integer): How often the page is read (default 60)
- `field` (string, required): A short name for the field, e.g. price
- `format` (string): Detected from the callback host when left out
- `label` (string): Optional name for your own reference
- `type` (string): The field's type (number for below and above)
- `url` (string, required): A public http(s) URL
- `value`: The number for below/above, or the text for contains
- `when` (string): Default changes; below and above compare numbers; contains looks for text in the value; gone fires when the field is no longer on the page

### `read_url` (~79 tokens)

Read Url

Free. Read a public web page or document (HTML, PDF, Word, Excel, CSV; up to 5 MB) as clean Markdown with its title. Up to 20 reads a minute per IP; for more, url_to_markdown is the paid version with no limit.

Input parameters:

- `url` (string, required): A public http(s) URL

### `extract_free` (~181 tokens)

Extract Free

Free. Extract structured JSON from a web page or text with a checked quote per field (up to 8 fields, Qwen3), 20 a day per IP. extract_data is the paid version: gpt-oss-120b, up to 25 fields, no limit.

Input parameters:

- `fields` (object, required): Field name -> "type: what it is" (types: string, number, integer, boolean), e.g. {"price": "number: the current price"}; a JSON Schema with properties also works
- `render` (boolean): Open the page in a real headless Chrome first, for pages built with JavaScript (slower; default false)
- `text` (string): Text to read instead of a URL (up to 60,000 characters)
- `url` (string): A public http(s) URL

### `watch_status` (~50 tokens)

Watch Status

Free. A field watch's status, current value and last 20 alerts, with the watch_id and secret that watch_field returned.

Input parameters:

- `secret` (string, required)
- `watch_id` (string, required)

### `stop_watch` (~41 tokens)

Stop Watch

Free. Stop a field watch, with the watch_id and secret that watch_field returned.

Input parameters:

- `secret` (string, required)
- `watch_id` (string, required)

### `service_info` (~32 tokens)

Service Info

Free. Lists every tool with its price and explains how payment works (x402 over MCP, USDC on Base).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox#diagnostics

## Score history

- 2026-11-04: 63
- 2026-11-03: 62
- 2026-11-02: 62
- 2026-11-01: 62
- 2026-10-31: 61
- 2026-10-30: 61
- 2026-10-29: 60
- 2026-10-28: 60
- 2026-10-27: 59
- 2026-10-26: 59
- 2026-10-25: 65
- 2026-10-24: 65

## Common questions

### What is the Agent Toolbox MCP server?

Agent Toolbox is an MCP server listed in the public MCP registry as io.github.zaffy18/agent-toolbox. Everyday tools for AI agents, paid per call with x402: images, markdown, speech-to-text, embeddings. This page covers its hosted endpoint (https://agent-toolbox.zafermemon87.workers.dev/mcp).

### Is the Agent Toolbox MCP server safe to use?

Agent Toolbox scores 63 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 Toolbox MCP server expose?

Agent Toolbox exposes 24 tools: generate_image, url_to_markdown, file_to_markdown, transcribe_audio, embed_text, and 19 more. Their descriptions and schemas cost roughly 3,044 tokens of context every time the server is loaded.

### Does the Agent Toolbox MCP server require authentication?

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

### Is the Agent Toolbox MCP server still maintained?

Agent Toolbox 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://agent-toolbox.zafermemon87.workers.dev/mcp
- Website: https://agent-toolbox.zafermemon87.workers.dev/llms.txt
- Changelog RSS feed: https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox.xml
- Changelog JSON feed: https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox.json
- HTML version of this page: https://verifymcp.io/servers/zaffy18-agent-toolbox/agent-toolbox