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.

Andreax

REMOTE · PAGOS.ANDREAX.DEV

270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.

−1 this week 72 Trust /100

Last scanned (10 hours ago)

Scores higher than 58% of remote servers

Reachable. Last reached 5 Nov 2026.

Category AI and Machine Learning

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 Security51
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 17790 tokens (~59/item across 298 items; 298 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 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 Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 298 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 299 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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 298 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.

  • 4 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 3 Nov 26 −2
    • Stability: pass → 0.90 functional
  • 30 Oct 26 0
    • New tool “asset-dossier” functional
  • 26 Oct 26 +1
    • Stability: 0.97 → pass security
    • New tool “verified-answer” functional
  • 24 Oct 26 −1
    • Stability: pass → 0.93 functional
  • 23 Oct 26 +1
    • Stability: 0.97 → pass security
  • 21 Oct 26 −1
    • Stability: pass → 0.93 functional
  • 20 Oct 26 +1
    • Stability: 0.97 → pass security
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 5 Nov 2026 · Probed https://pagos.andreax.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=andreax.dev CN=WE1,O=Google Trust Services,C=US 6 Oct 2026 4 Jan 2027 ECDSA 256 ECDSA-SHA256 5e57733c7e57d30e0ea4587ece3850f7
SANs: andreax.dev, *.andreax.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 insecure

Validation of pagos.andreax.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
andreax.dev. 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=31536000; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval' https://cdn.jsdelivr.net blob:; worker-src 'self' blob:; style-src 'self' 'unsafe-inline'; connect-src 'self' https://cdn.jsdelivr.net; img-src 'self' data: blob:; media-src 'self' blob:; frame-src 'self';
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(self), geolocation=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://pagos.andreax.dev/mcp Verified 200
http (plaintext) http://pagos.andreax.dev/mcp Served over HTTP 200
MCP tools · 298 exposed · ~17,706 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
ocr-multi-language ~43

ocr specialized for multi language [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyespipeline input

No output schema declared.

No examples provided.

ocr-receipts ~66

Scans receipt photos and extracts merchant, date, line items, tax, tip, total, and currency into structured JSON ready for expense reports o [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyespipeline input

No output schema declared.

No examples provided.

ocr-receipts-biz ~43

OCR receipts to structured JSON [x402: 0.05 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

ocr-receipts-biz2 ~47

ocr-receipts-biz2 [x402: 0.05 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

ocr-structured-json ~43

ocr specialized for structured json [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyespipeline input

No output schema declared.

No examples provided.

ocr-tables ~41

ocr specialized for tables [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyespipeline input

No output schema declared.

No examples provided.

option-expander ~71

Auto-created from research: Generador de escenarios y opciones alternativas que contrarresta el estrechamiento de futuros considerados por usuarios que confían ciegamente en recomendaciones de IA. [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

osint-signal ~61

OSINT(info): condensed market-vs-narrative signal + fear/greed. INFORMATION ONLY. input=asset. [x402: 5.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

palabras-clave ~58

Extrae palabras clave (TF-IDF + stopwords ES/EN). input: {texto, max?}. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

parser-bloque-contable ~55

Extrae movimientos estructurados de un bloque contable. input=texto contable. [x402: 0.03 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

pitch ~53

Genera un elevator pitch estructurado. input: {producto, audiencia?, duracion_seg?}. [x402: 0.05 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

pivotar-datos ~58

Tabla pivote sobre un CSV. input='<url_o_csv>||<indice>||<valores>'. [x402: 0.03 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

plan-estrategico ~52

Genera un plan estratégico. input=objetivo/contexto del plan. [x402: 0.1 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

podcast-pipeline ~64

WORKFLOW: episode title+structure+guest questions+show notes. input=topic. B2B: podcast studios pre-produce episodes. [x402: 15.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

portfolio-analysis ~61

TRADING(info): portfolio value, allocation and concentration analysis. INFORMATION ONLY. holdings={"bitcoin":0.5,"ethereum":2}. [x402: 10.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

precio-cripto ~57

Precio EN VIVO de una cripto (USD/COP). input=btc, eth, sol... [x402: 0.005 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

predictive-analytics ~53

PREMIUM: trend + short-term prediction + risks over your data. input=data/series. [x402: 10.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

preguntas ~50

Genera preguntas frecuentes (FAQ) sobre un tema. input=tema/producto. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

product-listing ~55

SMB: optimized ecommerce listing (title+bullets+desc+SEO). input=product data. [x402: 3.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

prompt-injection-scanner ~70

Auto-created from research: Analiza texto, documentos o instrucciones externas para detectar patrones de prompt injection indirecto y cumplimiento no autorizado antes de que un agente los procese. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

proofread ~47

Fix spelling and grammar of a text. input=text. [x402: 0.002 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyestexto a corregir

No output schema declared.

No examples provided.

proposal-draft ~50

SMB: draft a full commercial proposal/RFP response. input=requirements. [x402: 8.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

quarterly-review ~64

WORKFLOW: full QBR from your metrics + next-quarter plan. input=metrics+OKRs. B2B: leadership prep board reviews. [x402: 30.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

quick-summary ~45

CONSUMER: summary + keywords. input=text. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

read-pdf ~74

Download a PDF from a URL and return its extracted text. Let an agent read documents (reports, contracts, papers) pay-per-call. input=http(s) URL of a PDF. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesURL de un PDF

No output schema declared.

No examples provided.

read-url ~73

Download a web page and return its clean, readable text (no HTML or scripts). Let an agent read a URL's content pay-per-call. input=http(s) URL. [x402: 0.002 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesURL http(s) a leer

No output schema declared.

No examples provided.

real-estate-report ~68

VERTICAL(realestate): market report with prices/trends/risks + sources. input=market. B2B: agencies and investors evaluate an area. [x402: 20.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

reescribir-formal ~45

Auto-created from real demand (69 requests) [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

refactorizar ~55

Sugiere una versión refactorizada de un código. input='<lenguaje>||<codigo>'. [x402: 0.03 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

regex ~55

Generate a regex from a description. High-volume dev tool. input=what to capture. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesqué debe capturar el patrón

No output schema declared.

No examples provided.

reply ~55

Draft a reply to a message (email, chat, ticket). For support agents. input=message. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesmensaje a responder

No output schema declared.

No examples provided.

report ~82

Generate a written, structured research report on a topic: researches the web and synthesizes a 400-600 word report with cited sources. Premium service for when an agent needs analysis, not just links. input=topic. [x402: 0.5 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesTema del informe a redactar

No output schema declared.

No examples provided.

research ~74

Research a topic on the web and return a synthesis with cited sources (titles + URLs). Pay-per-query research for when an agent needs current information with sources. input=topic to research. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesTema o pregunta a investigar

No output schema declared.

No examples provided.

responder ~48

Genera una respuesta a un mensaje/email. input=mensaje a responder. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

resumen-conversacion ~51

Resume una conversación/hilo de texto. input=texto de la conversación. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

resumen-traduccion-demo ~54

Summarizes and translates to English (chains quick-summary -> fast-translate). [x402: 0.01 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada del pipeline

No output schema declared.

No examples provided.

resumir ~45

Resume un texto. input=texto a resumir. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

resumir-documento ~49

Resume un texto/documento. input=texto a resumir. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

retailer-intel ~69

VERTICAL(retail): competitor/pricing/assortment intelligence. input=retailer+region. B2B: retailers tune assortment and pricing with fresh data. [x402: 20.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

revisar-codigo ~43

Auto-created from real demand (77 requests) [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

revisar-seguridad ~52

Revisión de seguridad de código. input='<lenguaje>||<codigo>'. [x402: 4.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

rewrite-formal ~54

Rewrite a text in a formal, professional tone (same language). input=text. [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyestexto a reescribir

No output schema declared.

No examples provided.

risk-analysis ~58

PREMIUM (business): risk analysis of a decision/plan with mitigations. input=decision/plan. [x402: 0.12 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesdecisión/plan a evaluar

No output schema declared.

No examples provided.

rwa-report ~48

Yield and risk of 12 tokenized RWA funds, updated. [x402: 0.005 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

saas-churn-analysis ~65

VERTICAL(saas): churn diagnosis + retention levers. input=churn data. B2B: CS teams prioritize retention actions. [x402: 15.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

sales-email ~63

PREMIUM: write a sales/prospecting email (subject + body) from context. input=context. [x402: 0.02 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyescontexto del email (a quién, qué ofreces)

No output schema declared.

No examples provided.

screen-aware-assist ~52

PREMIUM: reads your screen (VLM) and assists. input=question. [x402: 2.0 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesservice input

No output schema declared.

No examples provided.

semantic-search ~99

Rank a list of documents by MEANING closeness to a query (cosine similarity over embeddings). Ready-to-use RAG, no need for the agent to run its own vector DB. input='query || doc 1 || doc 2 || ...' (|| separated). [x402: 0.003 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyes'consulta || doc1 || doc2 || ...'

No output schema declared.

No examples provided.

sensitive-information-detector ~58

Auto-created from research: Scans AI agent outputs for the disclosure of sensitive information and alerts on potential data breaches. [x402: 0.03 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyesentrada

No output schema declared.

No examples provided.

sentiment ~56

Classify the sentiment of a text (positive/negative/neutral) with a confidence score. input=text. [x402: 0.002 USDC on Base, pay-per-use]

NameTypeReqDescription
inputstringyestexto a analizar

No output schema declared.

No examples provided.

Install

How do I install the Andreax MCP server?

Andreax is a hosted endpoint at https://pagos.andreax.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 · pagos.andreax.dev

# add to Claude Code
claude mcp add --transport http moralito311-andr-andreax 'https://pagos.andreax.dev/mcp'
Common questions

What is the Andreax MCP server?

Andreax is an MCP server listed in the public MCP registry as io.github.moralito311-andr/andreax. 270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys. This page covers its hosted endpoint (https://pagos.andreax.dev/mcp).

Is the Andreax MCP server safe to use?

Andreax scores 72 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 Andreax MCP server expose?

Andreax exposes 298 tools: market-data, ai-inference, rwa-report, compress, distilla-compress, and 293 more. Their descriptions and schemas cost roughly 17,706 tokens of context every time the server is loaded.

Does the Andreax MCP server require authentication?

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

Is the Andreax MCP server still maintained?

Andreax 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.

What did VerifyMCP test on the Andreax MCP server?

VerifyMCP ran 12 checks on Andreax, 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 Andreax: 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.