Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Tlacuilo

REMOTE · TLACUILO-JET.VERCEL.APP

52 pay-per-call tools for AI agents over x402 (USDC): web, compliance, markets, token swaps

66 Trust /100

Last scanned (19 hours ago)

Scores higher than 51% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

Trust breakdown (7 categories)

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 Security63
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 9576 tokens (~156/item across 61 items; 61 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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; "msg_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 62 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
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 20 Nov 26 0
    • Schema quality: 8143 → 9576 ▼ functional
    • New tool “bridge_execute” functional
    • New tool “bridge_order” functional
    • New tool “bridge_status” functional
    • New tool “hyperliquid_account” functional
    • New tool “hyperliquid_markets” functional
    • New tool “hyperliquid_prepare” functional
    • New tool “hyperliquid_submit” functional
  • 19 Nov 26 +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.

  • 18 Nov 26 0
    • Tool “text_redact” rewrote its description, which is the text the model reads security
    • Schema quality: 7218 → 8143 ▼ functional
    • New tool “evm_swap_execute” functional
    • New tool “evm_swap_order” functional
    • New tool “solana_swap_execute” functional
    • New tool “solana_swap_order” functional
  • 17 Nov 26 0
    • Schema quality: 4913 → 7218 ▼ functional
    • Schema quality: 4913 → 6513 ▼ functional
    • New tool “sanctions_screen” functional
    • New tool “sec_fund_holdings” functional
    • New tool “text_redact” functional
    • New tool “company_br” functional
    • New tool “company_fr_search” functional
    • New tool “crypto_price” functional
    • New tool “fx_latest” functional
    • New tool “postal” functional
    • New tool “vat_eu” functional
    • New tool “weather” functional
    • New tool “web_render” functional
    • New tool “web_screenshot” functional
    • New tool “web_search” functional
  • 16 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
  • 15 Nov 26 64

    First indexed and scored.

Diagnostics

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 21 Nov 2026 · Probed https://tlacuilo-jet.vercel.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.vercel.app CN=WR1,O=Google Trust Services,C=US 31 Oct 2026 29 Jan 2027 RSA 2048 SHA256-RSA 9c5f0e6a35c955e113044c86848e4cd5
SANs: *.vercel.app
CN=WR1,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7fd9e2c2d2048a0474b627a26d0868a7
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of tlacuilo-jet.vercel.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
vercel.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://tlacuilo-jet.vercel.app/mcp Verified 200
http (plaintext) http://tlacuilo-jet.vercel.app/mcp HTTPS enforced 308 https://tlacuilo-jet.vercel.app/mcp
MCP tools · 61 exposed · ~9,511 tokens

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 →

Tool Tokens
text_redact ~227

Detects and redacts personal data in text before it is logged, stored or sent to a model: emails, phones, US SSNs, payment cards (Luhn-checked), IBANs (checksum-checked), IPv4/IPv6, URLs, dates of birth, street addresses, passport or ID numbers in context, and crypto wallet addresses. Returns the redacted text plus each finding with type, value and offsets. Modes: label ([EMAIL]), mask (****1234) or remove. Up to 200,000 characters per call; nothing leaves the server. Price: $0.003 USDC per call (x402).

NameTypeReqDescription
include_findingsstring–false to omit the findings array (default true)
modestring–label (default), mask or remove
textstringyesText to redact, up to 200000 characters
typesstring–Comma-separated subset of email,phone,ssn,credit_card,iban,ip,url,date_of_birth,address,passport,crypto_address (default all)

No output schema declared.

No examples provided.

token_verdict ~138

Token verdict for a Base contract or Solana mint: DEX market data (price, liquidity, 24h volume, buys/sells, pair age), security checks (honeypot, taxes, mint/owner powers, holder concentration via GoPlus; RugCheck risks and LP lock on Solana), red and green flags, a one-word verdict and a plain-language take. Entertainment, not trading advice. Price: $0.02 USDC per call (x402).

NameTypeReqDescription
addressstringyesToken contract (Base) or mint address (Solana)
chainstring–base or solana (default base)

No output schema declared.

No examples provided.

uma ~65

Current and historical UMA (Unidad de Medida y Actualización) values published by INEGI: daily, monthly and annual amounts with their effective dates. Price: $0.001 USDC per call (x402).

NameTypeReqDescription
aniostring–Year (default: current)

No output schema declared.

No examples provided.

vat_eu ~118

Validates an EU VAT number against the European Commission's VIES system, the check required for zero-rated intra-community invoices: valid or not, and the registered name and address when the member state publishes them. All 27 member states plus Northern Ireland (XI); Greece accepted as GR or EL. Price: $0.005 USDC per call (x402).

NameTypeReqDescription
vatstringyesVAT number with 2-letter country prefix, e.g. DE811115368, FR40303265045, ESB12345678

No output schema declared.

No examples provided.

weather ~159

Current weather and daily forecast up to 16 days for any city name or coordinates: temperature, feels-like, humidity, precipitation, wind, day/night and a plain-language condition now, plus daily highs, lows, rain probability, wind and sunrise/sunset. Metric or imperial units; local timezone resolved automatically. Price: $0.002 USDC per call (x402).

NameTypeReqDescription
citystring–City name, optionally with country, e.g. 'Austin, US'
daysstring–Forecast days, 1-16 (default 3)
latstring–Latitude (alternative to city)
lngstring–Longitude (alternative to city)
unitsstring–metric (default) or imperial

No output schema declared.

No examples provided.

web_read ~112

Read any public web page as clean, LLM-ready markdown: title, meta description, language and main content with navigation, ads and scripts removed. Follows redirects. Cheapest way to read a URL before deciding whether to pay for a full render. Price: $0.001 USDC per call (x402).

NameTypeReqDescription
max_charsstring–Maximum characters of markdown to return, 1000-200000 (default 60000)
urlstringyesPublic http(s) URL to read

No output schema declared.

No examples provided.

web_render ~172

Renders a public page in a real headless Chromium with JavaScript executed, then returns the result as clean markdown, plain text or HTML: single-page apps, infinite-scroll feeds, client-side dashboards and anything the cheap fetch-based reader returns empty for. Waits for the network to go quiet, optional extra settle time, navigation, ads and trackers removed. Price: $0.02 USDC per call (x402).

NameTypeReqDescription
formatstring–markdown (default), text or html
max_charsstring–Maximum characters to return, 1000-200000 (default 60000)
urlstringyesPublic http(s) URL to render
wait_msstring–Extra milliseconds to wait after the page loads, 0-8000 (default 0)

No output schema declared.

No examples provided.

web_screenshot ~214

Screenshot of a public page taken by a real headless Chromium after JavaScript runs, returned as a base64 JPEG or PNG with final URL, HTTP status and title. Viewport from 320x240 to 1920x2000, optional full-page capture and extra settle time. For visual checks, layout QA, archiving and vision-model input. Price: $0.03 USDC per call (x402).

NameTypeReqDescription
formatstring–jpeg (default, quality 70) or png
full_pagestring–true to capture the whole scrollable page (default false)
heightstring–Viewport height in pixels, 240-2000 (default 800)
urlstringyesPublic http(s) URL to capture
wait_msstring–Extra milliseconds to wait after load, 0-8000 (default 500)
widthstring–Viewport width in pixels, 320-1920 (default 1280)

No output schema declared.

No examples provided.

web_search ~178

Web search results as JSON: up to 30 organic results with rank, title, URL, domain and snippet, ads removed. Optional region (us-en, mx-es, de-de...) and recency filter (past day, week, month or year). No account, no key, no per-query quota to manage. Price: $0.005 USDC per call (x402).

NameTypeReqDescription
limitstring–Results to return, 1-30 (default 10)
qstringyesSearch query, up to 400 characters
regionstring–Region-language code such as us-en, mx-es, gb-en, de-de; wt-wt for no region (default)
timestring–Recency: d (day), w (week), m (month), y (year)

No output schema declared.

No examples provided.

web_tables ~148

Every HTML table on a public web page as structured JSON: title (caption or nearest heading), headers, rows as arrays and as records keyed by header, numeric columns detected and parsed to numbers, colspan and rowspan expanded, footnote markers removed. Selecting one table by index also returns it as CSV. Row count capped by max_rows. Price: $0.003 USDC per call (x402).

NameTypeReqDescription
indexstring–Zero-based table index; when given only that table is returned, with csv
max_rowsstring–Maximum rows per table, 1-5000 (default 200)
urlstringyesPublic http(s) URL of the page

No output schema declared.

No examples provided.

x402_find ~156

Which x402 API should I call for this task? Searches the Coinbase Bazaar catalog and ranks candidates by evidence of real use: distinct payers, repeat calls per payer, recency of payments and price. Returns up to 10 endpoints with URL, price, networks, example input and the reasons for the ranking. Price: $0.01 USDC per call (x402).

NameTypeReqDescription
limitstring–Results to return, 1-10 (default 5)
max_pricestring–Maximum USD price per call (optional)
needstringyesTask in plain words
networkstring–CAIP-2 network filter, e.g. eip155:8453 (optional)

No output schema declared.

No examples provided.

Install

How do I install the Tlacuilo MCP server?

Tlacuilo is a hosted endpoint at https://tlacuilo-jet.vercel.app/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 · tlacuilo-jet.vercel.app

# add to Claude Code
claude mcp add --transport http mastercobeos-tlacuilo 'https://tlacuilo-jet.vercel.app/mcp'
Common questions

What is the Tlacuilo MCP server?

Tlacuilo is an MCP server listed in the public MCP registry as io.github.mastercobeos/tlacuilo. 52 pay-per-call tools for AI agents over x402 (USDC): web, compliance, markets, token swaps. This page covers its hosted endpoint (https://tlacuilo-jet.vercel.app/mcp).

Is the Tlacuilo MCP server safe to use?

Tlacuilo scores 66 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 Tlacuilo MCP server expose?

Tlacuilo exposes 61 tools: catalog, health, web_read, x402_find, token_verdict, and 56 more. Their descriptions and schemas cost roughly 9,511 tokens of context every time the server is loaded.

Does the Tlacuilo MCP server require authentication?

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

Is the Tlacuilo MCP server still maintained?

Tlacuilo is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Tlacuilo MCP server?

VerifyMCP ran 12 checks on Tlacuilo, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Tlacuilo: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.