# io.github.Deesmo/arch-tools-mcp (remote · archtools.dev)

63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.

- Trust score: 75/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `arch-tools-mcp.onrender.com`: 27/100, [markdown](https://verifymcp.io/servers/deesmo-arch-tools-mcp/arch-tools-mcp-2.md), [page](https://verifymcp.io/servers/deesmo-arch-tools-mcp/arch-tools-mcp-2)
- remote · `archtools.dev`: 75/100 (this document), [markdown](https://verifymcp.io/servers/deesmo-arch-tools-mcp/archtools.md), [page](https://verifymcp.io/servers/deesmo-arch-tools-mcp/archtools)

## Channel facts

- Endpoint: `https://archtools.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.0.1`

## 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 2026-08-03.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 46/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 2488 tokens (~39/item across 63 items; 63 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 66% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http deesmo-arch-tools-mcp https://archtools.dev/mcp
```

### Codex

```toml
[mcp_servers.deesmo-arch-tools-mcp]
url = "https://archtools.dev/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add deesmo-arch-tools-mcp --url https://archtools.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  deesmo-arch-tools-mcp:
    url: "https://archtools.dev/mcp"
```

### Other

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

### 2026-08-03 (score 75, +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.

### 2026-08-01 (score 74, +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.

### 2026-07-31 (score 73, +7)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 65, +50)

- [security improvement] Authorization: unverified → pass
- [security improvement] HSTS header: fail → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: poor
- [functional] First check of Tool coverage: 66
- [functional] First check of Schema quality: pass

### 2026-07-28 (score 15)

First indexed and scored.

## MCP tools (63)

### `ai-generate` (~58 tokens)

AI-powered text generation using Claude (requires ANTHROPIC_API_KEY)

Input parameters:

- `max_tokens` (integer)
- `model` (string)
- `prompt` (string, required): Generation prompt
- `system` (string): Optional system prompt

### `ai-oracle` (~19 tokens)

AI reasoning engine with standard and deep analysis modes

### `barcode-generate` (~56 tokens)

Generate Code128 barcodes as SVG

Input parameters:

- `format` (string)
- `height` (integer)
- `include_text` (boolean)
- `value` (string, required): Value to encode
- `width` (integer)

### `browser-task` (~72 tokens)

Headless browser automation (click/type/extract) via Playwright — SSRF hardened

Input parameters:

- `action` (string)
- `selector` (string): CSS selector (required for click/type, optional for extract)
- `text` (string): Text for type action
- `url` (string, required): URL to open

### `check-domain` (~25 tokens)

Check if a domain is available or registered via RDAP. No API key needed.

### `convert-format` (~47 tokens)

Convert data between JSON, YAML, CSV, and XML formats

Input parameters:

- `data` (required): Data to convert (string or object)
- `from` (string, required)
- `to` (string, required)

### `crypto-fear-greed` (~21 tokens)

Crypto Fear & Greed Index with historical data

### `crypto-market-cap` (~26 tokens)

Top N cryptocurrencies by market cap with price, volume, and 24h change

### `crypto-news` (~18 tokens)

Latest crypto news headlines. Filter by token symbol

### `crypto-ohlcv` (~26 tokens)

OHLCV candlestick data for any crypto over 1-90 days

### `crypto-price` (~26 tokens)

Real-time price, 24h change, market cap, and volume for any cryptocurrency

### `crypto-sentiment` (~23 tokens)

Community sentiment, social stats, and price momentum for any cryptocurrency

### `currency-convert` (~62 tokens)

Convert between currencies using real-time exchange rates (170+ currencies)

Input parameters:

- `amount` (number, required): Amount to convert
- `from` (string, required): Source currency code (e.g. USD)
- `to` (string, required): Target currency code (e.g. EUR)

### `design-create` (~19 tokens)

Generate designs and images via DALL-E 3

### `diff-text` (~51 tokens)

Compare two text strings and return differences in unified, word, char, or JSON format

Input parameters:

- `format` (string)
- `modified` (string, required): Modified text
- `original` (string, required): Original text

### `domain-check` (~15 tokens)

Check domain availability via RDAP

### `email-find` (~19 tokens)

Find email addresses for a person at a company domain

### `email-send` (~15 tokens)

Send transactional emails via Resend

### `email-verify` (~34 tokens)

Deep email validation: syntax, MX record check, disposable domain detection

Input parameters:

- `email` (string, required): Email address to verify

### `extract-entities` (~53 tokens)

Named entity recognition: people, organizations, locations, dates, money, and more

Input parameters:

- `text` (string, required): Text to extract entities from
- `types` (array): Entity types to extract (default: all)

### `extract-metadata` (~50 tokens)

Extract metadata from text or URLs (word count, OG tags, headers, etc.)

Input parameters:

- `text` (string): Text to analyze
- `url` (string): URL to fetch and extract metadata from

### `extract-page` (~31 tokens)

Fetch a webpage and return clean text, metadata, and links

Input parameters:

- `url` (string, required): URL to extract

### `extract-pdf` (~34 tokens)

Extract text and tables from a PDF (requires PDF_EXTRACTOR_URL)

Input parameters:

- `url` (string, required): Public PDF URL

### `fact-check` (~49 tokens)

Verify the accuracy of a claim. Returns verdict (TRUE/FALSE/MIXED/UNVERIFIED/MISLEADING), confidence score, summary, and supporting/contradicting evidence with sources.

### `generate-hash` (~43 tokens)

Generate cryptographic hashes (sha256, sha512, md5, sha1)

Input parameters:

- `algorithm` (string)
- `input` (string, required): String to hash

### `generate-image` (~40 tokens)

Generate images from text prompts via DALL-E 3 (1024×1024, 1792×1024, 1024×1792).

### `generate-uuid` (~54 tokens)

Generate UUIDs (v1/v4), secure random tokens, and API-key-format strings

Input parameters:

- `count` (integer)
- `prefix` (string): Optional prefix for each UUID
- `type` (string)

### `html-to-markdown` (~42 tokens)

Convert HTML or any URL to clean Markdown

Input parameters:

- `html` (string): HTML string to convert
- `url` (string): URL to fetch and convert

### `image-generate` (~57 tokens)

Generate SVG images from text prompts via Claude

Input parameters:

- `height` (integer)
- `prompt` (string, required): Image description / prompt
- `quality` (string)
- `style` (string)
- `width` (integer)

### `image-remove-bg` (~15 tokens)

Remove background from any image

### `ip-lookup` (~45 tokens)

Geolocate any IP address — country, city, timezone, ISP, VPN/proxy detection

Input parameters:

- `ip` (string, required): IPv4 or IPv6 address to look up

### `jsonpath-query` (~41 tokens)

Run JSONPath expressions against any JSON payload

Input parameters:

- `json` (required): JSON object or string to query
- `path` (string, required): JSONPath expression starting with $

### `language-detect` (~34 tokens)

Detect the language of any text with confidence score and script identification

Input parameters:

- `text` (string, required): Text to detect language of

### `news-search` (~40 tokens)

Search for recent news articles on any topic. Returns title, URL, description, source, and publication date from Brave News, Tavily, or Serper.

### `ocr-extract` (~73 tokens)

Extract text from images or screenshots using AI vision (base64 or URL input)

Input parameters:

- `image_base64` (string): Base64-encoded image data
- `image_url` (string): Public URL of the image
- `media_type` (string)
- `prompt` (string): Optional custom extraction instruction

### `phone-validate` (~64 tokens)

Parse and validate phone numbers in any format — E.164, carrier type, country

Input parameters:

- `country_code` (string): ISO 3166-1 alpha-2 country code hint (e.g. US)
- `phone` (string, required): Phone number in any format

### `pii-detect` (~71 tokens)

Detect and optionally redact PII: names, emails, SSNs, credit cards, API keys, and more

Input parameters:

- `redact` (boolean): Return text with PII replaced
- `replacement` (string): Replacement string when redact is true
- `text` (string, required): Text to scan for PII

### `qr-code` (~55 tokens)

Generate QR codes from text or URLs (PNG data URL or SVG)

Input parameters:

- `format` (string)
- `margin` (integer)
- `text` (string, required): Text or URL to encode
- `width` (integer)

### `readability-score` (~37 tokens)

Compute Flesch-Kincaid readability, grade level, word count, and read time

Input parameters:

- `text` (string, required): Text to analyze

### `regex-generate` (~65 tokens)

Generate regular expressions from plain English with explanations and test results

Input parameters:

- `description` (string, required): Plain English description of what the regex should match
- `flags` (string): Regex flags (e.g. 'gi')
- `test_strings` (array): Optional strings to test against

### `research-report` (~37 tokens)

Generate a structured AI research report on any topic. Searches multiple sources and synthesizes findings into executive summary, key findings, and conclusion with citations.

### `rss-parse` (~42 tokens)

Fetch and parse RSS or Atom feeds into clean structured JSON

Input parameters:

- `limit` (integer)
- `url` (string, required): URL of the RSS or Atom feed

### `screenshot-capture` (~57 tokens)

Capture page metadata and screenshot URL for any public URL

Input parameters:

- `full_page` (boolean): Capture full scrollable page
- `height` (integer)
- `url` (string, required): URL to screenshot
- `width` (integer)

### `search-web` (~44 tokens)

Search the web and return structured results (Tavily/Serper or DuckDuckGo fallback)

Input parameters:

- `limit` (integer)
- `query` (string, required): Search query

### `semantic-search` (~16 tokens)

AI-powered semantic search across web content

### `send-email` (~20 tokens)

Send transactional emails via Resend — plain text or HTML.

### `sentiment-analysis` (~33 tokens)

Analyze text sentiment: positive/negative/neutral with score and emotion detection

Input parameters:

- `text` (string, required): Text to analyze

### `session-create` (~15 tokens)

Create a persistent AI conversation session

### `session-message` (~17 tokens)

Send a message in an existing AI session

### `summarize` (~51 tokens)

Summarize text in multiple styles: paragraph, bullets, tldr, headline, executive

Input parameters:

- `max_length` (integer)
- `style` (string)
- `text` (string, required): Text to summarize

### `text-to-speech` (~29 tokens)

Convert text to natural-sounding audio via ElevenLabs. Returns base64-encoded MP3.

### `timezone-convert` (~87 tokens)

Convert a datetime between any two IANA timezones

Input parameters:

- `datetime` (string): Datetime string to convert (ISO 8601). Defaults to now.
- `from_tz` (string): Source IANA timezone (e.g. America/New_York). Defaults to UTC.
- `to_tz` (string, required): Target IANA timezone (e.g. Asia/Tokyo)

### `token-lookup` (~24 tokens)

Search for any token by name or ticker, returns CoinGecko IDs

### `transcribe-audio` (~27 tokens)

Transcribe audio files to text via OpenAI Whisper. Supports 100+ languages.

### `transform-text` (~47 tokens)

Transform text: uppercase, lowercase, trim, reverse, slug, title, camel, snake, base64

Input parameters:

- `mode` (string)
- `text` (string, required): Text to transform

### `url-shorten` (~27 tokens)

Shorten any URL via TinyURL

Input parameters:

- `url` (string, required): URL to shorten

### `validate-data` (~36 tokens)

Validate JSON data against a JSON Schema

Input parameters:

- `data` (required): Data to validate
- `schema` (object, required): JSON Schema to validate against

### `video-generate` (~17 tokens)

Generate short video clips from text prompts

### `webhook-send` (~58 tokens)

POST a JSON payload to any webhook URL

Input parameters:

- `body`: JSON payload to send
- `headers` (object): Optional extra headers (safe headers only)
- `method` (string)
- `url` (string, required): Webhook endpoint URL

### `web-scrape` (~53 tokens)

Scrape and extract content from websites with optional CSS selector

Input parameters:

- `format` (string)
- `selector` (string): Optional CSS selector to extract specific content
- `url` (string, required): URL to scrape

### `web-search` (~65 tokens)

Real-time web search with AI-synthesized answer (requires TAVILY_API_KEY)

Input parameters:

- `include_answer` (boolean): Include AI-synthesized answer
- `max_results` (integer)
- `query` (string, required): Search query
- `search_depth` (string)

### `whois-lookup` (~46 tokens)

Look up domain registration info: registrar, created/expires dates, nameservers, status

Input parameters:

- `domain` (string, required): Domain name to look up (e.g. google.com)

### `workflow-agent` (~15 tokens)

Multi-step autonomous AI agent pipeline

## Diagnostics

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

## Score history

- 2026-08-03: 75
- 2026-08-02: 74
- 2026-08-01: 74
- 2026-07-31: 73
- 2026-07-30: 66
- 2026-07-29: 65
- 2026-07-28: 15

## Links

- Remote endpoint: https://archtools.dev/mcp
- Repository: https://github.com/Deesmo/Arch-AI-Tools
- Website: https://archtools.dev/
- Changelog RSS feed: https://verifymcp.io/servers/deesmo-arch-tools-mcp/archtools/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/deesmo-arch-tools-mcp/archtools/changelog.json
- HTML version of this page: https://verifymcp.io/servers/deesmo-arch-tools-mcp/archtools