io.github.Deesmo/arch-tools-mcp
REMOTE · ARCHTOOLS.DEV · 2 COMPONENTS
63 production tools for AI agents — one API key, pay per call in USDC (x402) or Stripe credits.
Available components
Last scanned (21 hours ago)
Scores higher than 98% of remote servers
Reachable. Last reached 4 Nov 2026.
Category AI and Machine Learning
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. How we score → Why this is hard to score →
Endpoint Security97
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- 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. View diagnostics → Pass
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability74
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 5444 tokens (~86/item across 63 items; 63 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management82
- Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 22 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 5 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "email-send" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 63 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 0
- Stability: pass → fail ▼ security
- Schema quality: 39 → 86 ▼ functional
- Tool coverage: 68% → 100% ▲ functional
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 3 Nov 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 2 Nov 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 1 Nov 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 31 Oct 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 30 Oct 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 29 Oct 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
- 28 Oct 26 0
- This server's schema is too large to store in full, so we cannot compare its tools day to day functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://archtools.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=archtools.dev | CN=WE1,O=Google Trust Services,C=US | 26 Oct 2026 | 24 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | a8700297c318469813b8db20d0cead4b |
| SANs: archtools.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of archtools.dev. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| archtools.dev. | present | 2371 | 13 | Verified |
| archtools.dev. | Verified address RRset verified with the apex keys |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 200 |
WWW-Authenticate challenge Bearer resource_metadata="https://archtools.dev/.well-known/oauth-protected-resource", scope="tools:read tools:execute"
Bearer resource_metadata="https://archtools.dev/.well-known/oauth-protected-resource", scope="tools:read tools:execute"| Header | Value |
|---|---|
| strict-transport-security | max-age=15552000; includeSubDomains; preload |
| content-security-policy | default-src 'self';script-src 'self' 'unsafe-inline' https://cdn.jsdelivr.net https://browser.sentry-cdn.com https://js.sentry-cdn.com https://www.clarity.ms https://*.clarity.ms https://assets.apollo.io https://cdnjs.cloudflare.com https://static.cloudflareinsights.com;script-src-attr 'unsafe-inline';style-src 'self' 'unsafe-inline' https://fonts.googleapis.com https://cdnjs.cloudflare.com;font-src 'self' https://fonts.gstatic.com;img-src 'self' data: https:;connect-src 'self' https://archtools.dev https://pay.coinbase.com https://*.sentry.io https://*.ingest.sentry.io https://www.clarity.ms https://*.clarity.ms https://assets.apollo.io https://*.apollo.io https://aplo-evnt.com https://*.aplo-evnt.com https://cloudflareinsights.com;base-uri 'self';form-action 'self';frame-ancestors 'self';object-src 'none';upgrade-insecure-requests |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | no-referrer |
Protected resource metadata
| Document | https://archtools.dev/.well-known/oauth-protected-resource |
|---|---|
| Retrieved | Yes |
| Resource | https://archtools.dev |
| Authorisation server | https://archtools.dev |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://archtools.dev/mcp | Verified | 200 | |
| http (plaintext) | http://archtools.dev/mcp | HTTPS enforced | 301 | https://archtools.dev/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ai-generate ~288
AI-powered text generation using Claude (requires ANTHROPIC_API_KEY)
| Name | Type | Req | Description |
|---|---|---|---|
| max_tokens | integer | – | Maximum output tokens (default 1000, served value capped at 4096). Credit cost is 20 plus 20 per 1,000 requested tokens above 1,000. |
| model | string | – | Explicit model; overrides mode. Accepts aliases claude, gpt/gpt4/gpt-4, gemini, grok (case-insensitive) or an exact id: claude-sonnet-4-6, claude-opus-4-6, claude-haiku-4-5-20251001, gpt-4o, gpt-4o-m… |
| prompt | string | yes | Generation prompt |
| system | string | – | Optional system prompt |
No output schema declared.
No examples provided.
ai-oracle ~122
AI reasoning engine with standard and deep analysis modes
| Name | Type | Req | Description |
|---|---|---|---|
| context | string | – | Optional background text for the analysis; only the first 8,000 characters are used. |
| question | string | yes | The question or problem to analyze, up to 10,000 characters. |
| reasoning_depth | string | – | standard (Sonnet, 2,048 tokens) or deep (Opus, 4,096 tokens, costs about 2x credits); any other value returns 400. x402-paid calls without a BYOK key are served at standard. |
No output schema declared.
No examples provided.
barcode-generate ~129
Generate Code128 barcodes as SVG
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Alias for type: code128 (default, up to 80 characters) or qr (a real QR code, up to 1,000 characters). Other values return 400. |
| height | integer | – | Output height in pixels for code128 (default 100, 30-1000); a QR code is always square. |
| value | string | yes | Value to encode |
| width | integer | – | Output width in pixels (default 250, 50-2000); the barcode is scaled to fit. |
No output schema declared.
No examples provided.
browser-task ~84
Fetch a public page and extract its text or HTML, optionally by CSS selector (static HTML only: no JavaScript, clicking or typing)
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | extract = visible text, html = inner HTML of the selected element |
| selector | string | – | Optional CSS selector (defaults to the page body) |
| url | string | yes | Public page URL to fetch |
No output schema declared.
No examples provided.
check-domain ~58
Check if a domain is available or registered via RDAP. No API key needed.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Domain name to look up via RDAP, e.g. example.com; a leading http(s):// and any path are stripped. |
No output schema declared.
No examples provided.
convert-format ~118
Convert data between JSON, YAML, CSV, and XML formats
| Name | Type | Req | Description |
|---|---|---|---|
| data | – | yes | Data to convert (string or object) |
| from | string | yes | Format of the input: json, yaml, csv, xml, text (or string), or base64. Unsupported formats return 400. |
| to | string | yes | Target format: json, yaml, csv or xml when from is a structured format; base64 or hex when from is text; text (or string) or hex when from is base64. Unsupported targets return 400. |
No output schema declared.
No examples provided.
crypto-fear-greed ~54
Crypto Fear & Greed Index with historical data
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Number of daily Fear & Greed index entries to return, newest first (default 7, clamped to 1-30). |
No output schema declared.
No examples provided.
crypto-market-cap ~82
Top N cryptocurrencies by market cap with price, volume, and 24h change
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Fiat or crypto currency code for prices, e.g. usd or eur (lowercased; default usd). |
| limit | integer | – | Number of top coins by market cap to return (default 10, clamped to 1-100). |
No output schema declared.
No examples provided.
crypto-news ~78
Latest crypto news headlines. Filter by token symbol
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of articles (default 10, clamped to 1-20). |
| symbol | string | – | Optional coin to filter headlines by, as a ticker or name, e.g. BTC or bitcoin; alias: coin. Omit for general crypto news. |
No output schema declared.
No examples provided.
crypto-ohlcv ~139
OHLCV candlestick data for any crypto over 1-90 days
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Quote currency in lowercase, e.g. usd (default usd). |
| days | integer | – | How many days of OHLC candles to return, passed to CoinGecko as-is (CoinGecko accepts 1, 7, 14, 30, 90, 180, 365); default 7. |
| symbol | string | yes | Coin as a CoinGecko id or common ticker, e.g. bitcoin or BTC (tickers like BTC/ETH/SOL are mapped to ids); alias: coin. |
No output schema declared.
No examples provided.
crypto-price ~100
Real-time price, 24h change, market cap, and volume for any cryptocurrency
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | Quote currency in lowercase, e.g. usd or eur (default usd); the server does not lowercase it, so always send lowercase. |
| symbol | string | yes | Coin as a CoinGecko id or common ticker, e.g. bitcoin or BTC (tickers like BTC/ETH/SOL are mapped to ids); alias: coin. |
No output schema declared.
No examples provided.
crypto-sentiment ~59
Community sentiment, social stats, and price momentum for any cryptocurrency
| Name | Type | Req | Description |
|---|---|---|---|
| symbol | string | yes | Full CoinGecko coin id, e.g. bitcoin or ethereum (lowercased). Tickers like BTC are NOT mapped and return 404. |
No output schema declared.
No examples provided.
currency-convert ~62
Convert between currencies using real-time exchange rates (170+ currencies)
| Name | Type | Req | Description |
|---|---|---|---|
| amount | number | yes | Amount to convert |
| from | string | yes | Source currency code (e.g. USD) |
| to | string | yes | Target currency code (e.g. EUR) |
No output schema declared.
No examples provided.
design-create ~156
Generate designs and images via DALL-E 3
| Name | Type | Req | Description |
|---|---|---|---|
| n | integer | – | Number of images; always capped at 1. |
| prompt | string | yes | Description of the image to generate with gpt-image-1, e.g. 'a watercolor fox in a forest'; screened by content moderation. |
| quality | string | – | Image quality: low, medium or high (aliases: standard/vivid/natural = medium, hd = high); any other value becomes medium. High quality costs more credits; x402-paid calls are capped at medium. |
| size | string | – | Image size in pixels; other values fall back to 1024x1024 (x402-paid calls are always 1024x1024). |
No output schema declared.
No examples provided.
diff-text ~71
Compare two text strings and return differences in unified, word, char, or JSON format
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | Diff granularity: words (default), chars, or lines (unified is the same as lines). |
| modified | string | yes | Modified text |
| original | string | yes | Original text |
No output schema declared.
No examples provided.
domain-check ~54
Check domain availability via RDAP
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Domain name to check for registration via RDAP, e.g. example.com; lowercased, and a leading http(s):// and any path are stripped. |
No output schema declared.
No examples provided.
email-find ~105
Find email addresses for a person at a company domain
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Company domain to search with Hunter.io, e.g. stripe.com. |
| first_name | string | – | Person's first name; with last_name, switches to a single-person email lookup. Ignored unless last_name is also given. |
| last_name | string | – | Person's last name; with first_name, switches to a single-person email lookup. Ignored unless first_name is also given. |
No output schema declared.
No examples provided.
email-send ~158
Send transactional emails via Resend
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Plain-text body (up to 10,000 chars used). Either body or html is required. |
| from | string | – | Custom sender address; only honored when the server has ALLOW_CUSTOM_EMAIL_FROM=true, otherwise the default Arch Tools sender is used. |
| html | string | – | HTML body (up to 20,000 chars used; script tags and inline on* handlers are stripped). Either body or html is required. |
| subject | string | yes | Email subject line, 200 characters or fewer. |
| to | string | yes | One recipient email address, e.g. alice@example.com; must contain @ and may not contain commas or newlines (single recipient only). |
No output schema declared.
No examples provided.
email-verify ~34
Deep email validation: syntax, MX record check, disposable domain detection
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | Email address to verify |
No output schema declared.
No examples provided.
extract-entities ~53
Named entity recognition: people, organizations, locations, dates, money, and more
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Text to extract entities from |
| types | array | – | Entity types to extract (default: all) |
No output schema declared.
No examples provided.
extract-metadata ~50
Extract metadata from text or URLs (word count, OG tags, headers, etc.)
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | – | Text to analyze |
| url | string | – | URL to fetch and extract metadata from |
No output schema declared.
No examples provided.
extract-page ~31
Fetch a webpage and return clean text, metadata, and links
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | URL to extract |
No output schema declared.
No examples provided.
extract-pdf ~34
Extract text and tables from a PDF (requires PDF_EXTRACTOR_URL)
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Public PDF URL |
No output schema declared.
No examples provided.
fact-check ~87
Verify the accuracy of a claim. Returns verdict (TRUE/FALSE/MIXED/UNVERIFIED/MISLEADING), confidence score, summary, and supporting/contradicting evidence with sources.
| Name | Type | Req | Description |
|---|---|---|---|
| claim | string | yes | The statement to fact-check, e.g. 'The Great Wall of China is visible from space'; may also be sent as a ?claim= query parameter. |
No output schema declared.
No examples provided.
generate-hash ~68
Generate cryptographic hashes (sha256, sha512, md5, sha1)
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm | string | – | Hash algorithm: sha256 (default), sha512, sha384, sha1 or md5; other values return 400. |
| input | string | yes | String to hash |
No output schema declared.
No examples provided.
generate-image ~150
Generate images from text prompts via DALL-E 3 (1024×1024, 1792×1024, 1024×1792).
| Name | Type | Req | Description |
|---|---|---|---|
| prompt | string | yes | Description of the image to generate with gpt-image-1; screened by content moderation. |
| quality | string | – | Image quality: low, medium or high (aliases: standard/vivid/natural = medium, hd = high); any other value becomes medium. High quality costs more credits; x402-paid calls are capped at medium. |
| size | string | – | Image size in pixels; other values fall back to 1024x1024 (x402-paid calls are always 1024x1024). |
No output schema declared.
No examples provided.
generate-uuid ~107
Generate UUIDs (v1/v4), secure random tokens, and API-key-format strings
| Name | Type | Req | Description |
|---|---|---|---|
| count | integer | – | How many values to generate (default 1, clamped to 1-100). |
| prefix | string | – | Optional prefix for each UUID |
| type | string | – | Alias for version: v1 for a timestamp-based UUID; any other value (default v4) gives a random v4 UUID (or the api_key/token value selected by format). |
No output schema declared.
No examples provided.
html-to-markdown ~42
Convert HTML or any URL to clean Markdown
| Name | Type | Req | Description |
|---|---|---|---|
| html | string | – | HTML string to convert |
| url | string | – | URL to fetch and convert |
No output schema declared.
No examples provided.
image-generate ~81
Generate SVG images from text prompts via Claude
| Name | Type | Req | Description |
|---|---|---|---|
| height | integer | – | SVG height in pixels written into the model prompt and viewBox (default 300; not validated). |
| prompt | string | yes | Image description / prompt |
| width | integer | – | SVG width in pixels written into the model prompt and viewBox (default 400; not validated). |
No output schema declared.
No examples provided.
image-remove-bg ~121
Remove background from any image
| Name | Type | Req | Description |
|---|---|---|---|
| image_base64 | string | – | Base64-encoded image bytes; used instead of image_url when both are given. Either image_url or image_base64 is required. |
| image_url | string | – | Public http(s) URL of the image (downloaded by the server, max about 22 MB). Either image_url or image_base64 is required. |
| size | string | – | Output resolution for remove.bg: auto, preview, full, or hd (hd is sent as full); other values return 400. |
No output schema declared.
No examples provided.
ip-lookup ~45
Geolocate any IP address — country, city, timezone, ISP, VPN/proxy detection
| Name | Type | Req | Description |
|---|---|---|---|
| ip | string | yes | IPv4 or IPv6 address to look up |
No output schema declared.
No examples provided.
jsonpath-query ~41
Run JSONPath expressions against any JSON payload
| Name | Type | Req | Description |
|---|---|---|---|
| json | – | yes | JSON object or string to query |
| path | string | yes | JSONPath expression starting with $ |
No output schema declared.
No examples provided.
language-detect ~34
Detect the language of any text with confidence score and script identification
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Text to detect language of |
No output schema declared.
No examples provided.
news-search ~99
Search for recent news articles on any topic. Returns title, URL, description, source, and publication date from Brave News, Tavily, or Serper.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of articles (default 5, capped at 10); may also be sent as ?limit=. |
| query | string | yes | News search query, e.g. 'OpenAI funding'; may also be sent as a ?query= query parameter. |
No output schema declared.
No examples provided.
ocr-extract ~122
Extract text from images or screenshots using AI vision (base64 or URL input)
| Name | Type | Req | Description |
|---|---|---|---|
| image_base64 | string | – | Base64-encoded image data |
| image_url | string | – | Public URL of the image |
| media_type | string | – | MIME type of image_base64: image/jpeg (default), image/png, image/gif or image/webp; other values fall back to image/jpeg. Not used when the image is downloaded from image_url (the download's Content… |
| prompt | string | – | Optional custom extraction instruction |
No output schema declared.
No examples provided.
phone-validate ~64
Parse and validate phone numbers in any format — E.164, carrier type, country
| Name | Type | Req | Description |
|---|---|---|---|
| country_code | string | – | ISO 3166-1 alpha-2 country code hint (e.g. US) |
| phone | string | yes | Phone number in any format |
No output schema declared.
No examples provided.
pii-detect ~71
Detect and optionally redact PII: names, emails, SSNs, credit cards, API keys, and more
| Name | Type | Req | Description |
|---|---|---|---|
| redact | boolean | – | Return text with PII replaced |
| replacement | string | – | Replacement string when redact is true |
| text | string | yes | Text to scan for PII |
No output schema declared.
No examples provided.
qr-code ~113
Generate QR codes from text or URLs (PNG data URL or SVG)
| Name | Type | Req | Description |
|---|---|---|---|
| error_correction | string | – | QR error-correction level: L, M (default), Q or H. |
| format | string | – | Output format: png (default, returned as a data URL) or svg (SVG markup); any other value returns png. |
| size | integer | – | Image size in pixels (default 256, clamped to 64-1024). |
| text | string | yes | Text or URL to encode |
No output schema declared.
No examples provided.
readability-score ~37
Compute Flesch-Kincaid readability, grade level, word count, and read time
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Text to analyze |
No output schema declared.
No examples provided.
regex-generate ~65
Generate regular expressions from plain English with explanations and test results
| Name | Type | Req | Description |
|---|---|---|---|
| description | string | yes | Plain English description of what the regex should match |
| flags | string | – | Regex flags (e.g. 'gi') |
| test_strings | array | – | Optional strings to test against |
No output schema declared.
No examples provided.
research-report ~110
Generate a structured AI research report on any topic. Searches multiple sources and synthesizes findings into executive summary, key findings, and conclusion with citations.
| Name | Type | Req | Description |
|---|---|---|---|
| depth | string | – | standard (5 sources, concise report) or deep (10 sources, advanced search, longer report); any value other than deep behaves as standard. |
| query | string | yes | Research topic or question, e.g. 'state of solid-state batteries'; alias: topic (also accepted as ?query= or ?topic= query parameters). |
No output schema declared.
No examples provided.
rss-parse ~57
Fetch and parse RSS or Atom feeds into clean structured JSON
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Maximum number of feed items to return (default 20; no upper cap). |
| url | string | yes | URL of the RSS or Atom feed |
No output schema declared.
No examples provided.
screenshot-capture ~42
Get a page's title, description, Open Graph image and a text preview (metadata only; no rendered screenshot)
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Public page URL |
No output schema declared.
No examples provided.
search-web ~69
Search the web and return structured results (Tavily/Serper or DuckDuckGo fallback)
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Number of results to return (default 5, clamped to 1-10); num_results is accepted as an alias. |
| query | string | yes | Search query |
No output schema declared.
No examples provided.
semantic-search ~136
AI-powered semantic search across web content
| Name | Type | Req | Description |
|---|---|---|---|
| documents | array | – | Optional list of your own text documents to rank against the query locally by keyword overlap instead of searching the web with Exa. |
| num_results | integer | – | Number of results (default 5, clamped to 1-20); alias: limit, which takes precedence if both are sent. |
| query | string | yes | Natural-language search query, e.g. 'startups building AI agents for accounting'. |
| type | string | – | Exa search mode: neural (default) or keyword; other values return 400. Ignored when documents is provided. |
No output schema declared.
No examples provided.
send-email ~163
Send transactional emails via Resend — plain text or HTML.
| Name | Type | Req | Description |
|---|---|---|---|
| body | string | – | Plain-text body (up to 10,000 chars used). Either body or html is required. |
| from | string | – | Custom sender address; only honored when the server has ALLOW_CUSTOM_EMAIL_FROM=true, otherwise the default Arch Tools sender is used. |
| html | string | – | HTML body (up to 20,000 chars used; script tags and inline on* handlers are stripped). Either body or html is required. |
| subject | string | yes | Email subject line, 200 characters or fewer. |
| to | string | yes | One recipient email address, e.g. alice@example.com; must contain @ and may not contain commas or newlines (single recipient only). |
No output schema declared.
No examples provided.
sentiment-analysis ~33
Analyze text sentiment: positive/negative/neutral with score and emotion detection
| Name | Type | Req | Description |
|---|---|---|---|
| text | string | yes | Text to analyze |
No output schema declared.
No examples provided.
session-create ~145
Create a persistent AI conversation session
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | Model for the session: alias claude, gpt, gpt4 or gpt-4 (case-insensitive), or an exact id; other values return 400. Default claude-sonnet-4-6. x402-paid sessions are pinned to claude-sonnet-4-6 for… |
| namespace | string | yes | Required label grouping this conversation session, e.g. 'support-bot' (truncated to 100 chars). |
| system_prompt | string | – | Optional system prompt for every turn in the session (truncated to 4,000 chars); alias: system. |
No output schema declared.
No examples provided.
session-message ~72
Send a message in an existing AI session
| Name | Type | Req | Description |
|---|---|---|---|
| message | string | yes | The user message to send in the session, up to 10,000 characters. |
| session_id | string | yes | Session id returned by session-create, e.g. sess_3f2a...; must belong to the same caller. |
No output schema declared.
No examples provided.
summarize ~65
Summarize text in multiple styles: paragraph, bullets, tldr, headline, executive
| Name | Type | Req | Description |
|---|---|---|---|
| style | string | – | Summary style: paragraph (default), bullets, tldr, headline or executive; unknown values fall back to paragraph. |
| text | string | yes | Text to summarize |
No output schema declared.
No examples provided.
How do I install the io.github.Deesmo/arch-tools-mcp server?
io.github.Deesmo/arch-tools-mcp is a hosted endpoint at https://archtools.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.
remote · archtools.dev
claude mcp add --transport http deesmo-arch-tools-mcp 'https://archtools.dev/mcp'
What is the io.github.Deesmo/arch-tools-mcp server?
io.github.Deesmo/arch-tools-mcp is listed in the public MCP registry as io.github.Deesmo/arch-tools-mcp. 63 production tools for AI agents, one API key, pay per call in USDC (x402) or Stripe credits. This page covers its hosted endpoint (https://archtools.dev/mcp).
Is the io.github.Deesmo/arch-tools-mcp server safe to use?
io.github.Deesmo/arch-tools-mcp scores 90 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 io.github.Deesmo/arch-tools-mcp server expose?
io.github.Deesmo/arch-tools-mcp exposes 63 tools: ai-generate, ai-oracle, barcode-generate, browser-task, check-domain, and 58 more. Their descriptions and schemas cost roughly 5,444 tokens of context every time the server is loaded.
Does the io.github.Deesmo/arch-tools-mcp server require authentication?
Yes. io.github.Deesmo/arch-tools-mcp asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the io.github.Deesmo/arch-tools-mcp server still maintained?
io.github.Deesmo/arch-tools-mcp 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.