Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Funktioniert in Claude im Web, auf dem Desktop und auf dem Handy:
https://pagos.andreax.dev/mcpFühre das in deinem Terminal aus
claude mcp add --transport http andreax https://pagos.andreax.dev/mcpIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"andreax": {
"url": "https://pagos.andreax.dev/mcp"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"andreax": {
"type": "http",
"url": "https://pagos.andreax.dev/mcp"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
ChatGPT verbindet sich nur mit Servern im Internet:
https://pagos.andreax.dev/mcpMenünamen können sich je nach Tarif und mit der Zeit leicht unterscheiden.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Tool-Namen und -Beschreibungen genau so, wie der Server sie am 8. Nov. 2026 gemeldet hat. Geschrieben hat sie der Entwickler, nicht wir; wir zeigen sie als reinen Text.
market-dataSpot USDC/COP price and market depth (premium data). [x402: 0.001 USDC on Base, pay-per-use]
ai-inferenceModel answer to your query (pay-per-use AI compute). [x402: 0.002 USDC on Base, pay-per-use]
rwa-reportYield and risk of 12 tokenized RWA funds, updated. [x402: 0.005 USDC on Base, pay-per-use]
compressCompress a prompt into dense language and return the version with fewer tokens (typical 20-40% saving). Use it BEFORE sending prompts to any LLM to cut token cost without losing meaning. input=text to compress. [x402: 0.001 USDC on Base, pay-per-use]
distilla-compressDistilla (branded, real PyPI package): compress a prompt to dense language, same meaning, fewer tokens. input=prompt to compress. [x402: 0.02 USDC on Base, pay-per-use]
distilla-evocation-scoreDistilla: score how dense a prompt already is, 0-100 (higher = less filler to cut). input=prompt to score. [x402: 0.01 USDC on Base, pay-per-use]
distilla-identityDistilla: generate 7 dense identity aphorisms for a system from its description. input=system description. [x402: 0.05 USDC on Base, pay-per-use]
inferenceReturn an LLM (Kimi/DeepSeek) answer to your query. General-purpose, pay-per-call inference for when an agent needs a model response. input=your query as text. [x402: 0.005 USDC on Base, pay-per-use]
fxQuote a currency conversion into USDC with spread (e.g. COP->USDC, USD->USDC). Get stablecoin exchange rates. input=' '. [x402: 0.001 USDC on Base, pay-per-use]
researchResearch 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]
read-urlDownload 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]
reportGenerate 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]
crypto-priceReturn the LIVE price of a cryptocurrency in USD and COP with its 24h change (real market data). High volume for agents that need prices. input=symbol or id (btc, eth, sol, usdc...). [x402: 0.005 USDC on Base, pay-per-use]
embeddingsTurn text into a vector (embedding) for semantic search, RAG, clustering or memory. The building block every AI agent needs. High volume. input=text. [x402: 0.001 USDC on Base, pay-per-use]
semantic-searchRank 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]
read-pdfDownload 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]
wallet-balanceReturn the on-chain balance (ETH and USDC) of an address on the Base network. Live on-chain read for agents verifying funds or balances. input=0x address. [x402: 0.002 USDC on Base, pay-per-use]
ocrOCR: extract text from an image (JPG/PNG) or a PDF, including scanned PDFs with no text layer. Local engine (Tesseract 5), Spanish and English. Upload the file via multipart (field 'archivo') or send it as 'archivo_b64' in JSON. Optional 'lang' (spa|eng|spa+en [x402: 0.004 USDC o
visionComputer vision: describe or analyze an image with a LOCAL multimodal model (llava). For agents that need to 'see' (describe scenes, read diagrams, classify images). Upload the image via multipart or as 'archivo_b64'; 'input' = the question or instruction abou [x402: 0.008 USDC o
transcribeTranscribe an audio file to text (speech-to-text) with LOCAL Whisper, automatic language detection. For agents processing voice notes, calls or podcasts. Upload the audio via multipart or as 'archivo_b64'. Optional 'lang' (es|en|...). [x402: 0.01 USDC on Base, pay-per-use]
smart-documentPremium PIPELINE in a single call: takes an image or PDF, extracts its text (OCR), summarizes it and translates the summary to the target language. For agents that need to 'understand a document' end-to-end (invoices, contracts, letters, papers) without orches [x402: 0.03 USDC on
meeting-minutesPremium PIPELINE in a single call: takes an audio (meeting, voice note, call), transcribes it with local Whisper and writes MINUTES with Summary, Decisions and Tasks. For agents/teams turning a recording into actionable minutes without orchestrating services. [x402: 0.04 USDC on
deep-research-reportPREMIUM: full research report with cited web sources. input=topic. [x402: 5.0 USDC on Base, pay-per-use]
screen-aware-assistPREMIUM: reads your screen (VLM) and assists. input=question. [x402: 2.0 USDC on Base, pay-per-use]
voice-clone-ttsPREMIUM: returns SSML ready for your TTS engine. input=text. [x402: 3.0 USDC on Base, pay-per-use]
predictive-analyticsPREMIUM: trend + short-term prediction + risks over your data. input=data/series. [x402: 10.0 USDC on Base, pay-per-use]
multi-agent-debatePREMIUM: multi-model debate (DeepSeek+Kimi) then a judged conclusion. input=question. [x402: 7.0 USDC on Base, pay-per-use]
code-review-securityPREMIUM: security-focused code review by severity. input=code. [x402: 4.0 USDC on Base, pay-per-use]
market-intelligencePREMIUM: market intelligence with live data + scenarios. input=asset/market. [x402: 8.0 USDC on Base, pay-per-use]
autonomous-workflowPREMIUM: executable step-by-step autonomous workflow plan. input=goal. [x402: 15.0 USDC on Base, pay-per-use]
content-pipelinePREMIUM: full content pipeline (post + variants + hashtags). input=brief. [x402: 5.0 USDC on Base, pay-per-use]
compliance-auditPREMIUM: compliance/legal-risk audit by severity. input=document/policy. [x402: 20.0 USDC on Base, pay-per-use]
comprimirCONSUMER: compress a prompt to dense language keeping meaning (<=50%). input=text. B2B: save LLM tokens in pipelines. [x402: 0.001 USDC on Base, pay-per-use]
contar-tokensCONSUMER: exact token count (tiktoken) for a model. input=text, modelo=optional. B2B: budget LLM calls. [x402: 0.001 USDC on Base, pay-per-use]
interpretarCONSUMER: detect intent + categories + sentiment. input=message, categorias=optional. B2B: ticket routing, chatbots. [x402: 0.001 USDC on Base, pay-per-use]
fast-translateCONSUMER: translate + proofread to any language. input=text, to=lang. [x402: 0.05 USDC on Base, pay-per-use]
quick-summaryCONSUMER: summary + keywords. input=text. [x402: 0.02 USDC on Base, pay-per-use]
email-polishCONSUMER: rewrite email formal + proofread. input=draft, tono=optional. [x402: 0.05 USDC on Base, pay-per-use]
doc-extractCONSUMER: extract structured JSON from a document. input=text, campos=optional. [x402: 0.1 USDC on Base, pay-per-use]
audio-to-textCONSUMER: clean + summarize a transcript. input/transcript=text. [x402: 0.2 USDC on Base, pay-per-use]
image-describeCONSUMER: describe image + entities. image=base64|url. [x402: 0.1 USDC on Base, pay-per-use]
code-explainCONSUMER: explain code + basic improvements. input=code. [x402: 0.1 USDC on Base, pay-per-use]
topic-classifyCONSUMER: classify topic + entities. input=text, labels=optional. [x402: 0.02 USDC on Base, pay-per-use]
language-detectCONSUMER: detect language (ISO code). input=text. [x402: 0.001 USDC on Base, pay-per-use]
fact-check-quickCONSUMER: quick fact-check with web sources. input=claim. [x402: 0.1 USDC on Base, pay-per-use]
seo-articleSMB: keyword-researched long-form SEO article + meta tags. input=topic. [x402: 3.0 USDC on Base, pay-per-use]
competitor-scanSMB: competitor research + SWOT + positioning + how-to-win. input=company. [x402: 5.0 USDC on Base, pay-per-use]
lead-enrichSMB: enrich a B2B lead + outreach angle + subject line. input=domain/company. [x402: 2.0 USDC on Base, pay-per-use]
social-calendarSMB: 14-day content calendar (posts+hashtags+times). input=brand, red=optional. [x402: 4.0 USDC on Base, pay-per-use]
product-listingSMB: optimized ecommerce listing (title+bullets+desc+SEO). input=product data. [x402: 3.0 USDC on Base, pay-per-use]
meeting-briefSMB: pre-meeting brief + talking points + questions. input=person/company. [x402: 2.0 USDC on Base, pay-per-use]
invoice-batchSMB: extract structured data + totals from many invoices. input=invoice texts. [x402: 4.0 USDC on Base, pay-per-use]
customer-replySMB: classify a support ticket + draft the reply. input=ticket, tono=optional. [x402: 1.0 USDC on Base, pay-per-use]
blog-repurposeSMB: repurpose 1 article into thread+LinkedIn+newsletter+TLDR. input=article. [x402: 3.0 USDC on Base, pay-per-use]
proposal-draftSMB: draft a full commercial proposal/RFP response. input=requirements. [x402: 8.0 USDC on Base, pay-per-use]
market-research-reportENTERPRISE: full market report (TAM/SAM/SOM, trends, competitors) + sources. input=market. [x402: 25.0 USDC on Base, pay-per-use]
due-diligenceENTERPRISE: company due-diligence dossier + red flags (public sources). input=company. [x402: 50.0 USDC on Base, pay-per-use]
business-planENTERPRISE: complete business plan from an idea. input=business idea. [x402: 40.0 USDC on Base, pay-per-use]
technical-auditENTERPRISE: architecture/stack audit by severity + 90-day roadmap. input=system description. [x402: 30.0 USDC on Base, pay-per-use]
investor-deck-copyENTERPRISE: pitch-deck copy slide-by-slide + narrative. input=business. [x402: 35.0 USDC on Base, pay-per-use]
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 9. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto moralito311-andr bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Antwort in 226 ms (HTTP 200)
Keine Anmeldung nötig
Wir haben 60 Tool-Beschreibungen gelesen und keine versteckten Anweisungen an die KI gefunden
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 3 von 3 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft in der Cloud des Entwicklers. Du verbindest dich übers Internet, ohne etwas zu installieren, aber was du sendest, läuft über die Server des Entwicklers.
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.2.0) kam vor 42 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Er verbindet sich per URL, also funktionieren auch Apps, die Remote-MCP-Server akzeptieren, zum Beispiel ChatGPT im Entwicklermodus.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, erateradar
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:↓ Downloads pro Wochei★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Open E-rate network bids (Form 470s) from USAC public data, near a ZIP or in a state.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
Remote MCP server: https://pagos.andreax.dev/mcp (Streamable HTTP, JSON-RPC)
Andreax is a remote MCP server with 270 pay-per-call tools for AI agents — text, code, documents, audio, web research and on-chain data. There is no signup and no API key: each call is paid individually with x402 in USDC on Base, from $0.001 per call.
transferWithAuthorization; the settlement gas is paid by Andreax.?sample=1 and returns an example output at no cost.GET https://pagos.andreax.dev/.well-known/x402.jsonThis repository only contains the public listing (README + directory metadata). The server itself
is hosted; there is nothing to install.
mcp-remote){
"mcpServers": { "andreax": { "command": "npx", "args": ["-y", "mcp-remote", "https://pagos.andreax.dev/mcp"] } } }
Add a remote server with URL https://pagos.andreax.dev/mcp (transport: Streamable HTTP, auth: none).
npm install @andreax-tools/sdk
tools/list is free.tools/call without payment returns an x402 v2 challenge: exact amount, network (eip155:8453), asset (USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913) and recipient.x_payment, or the X-PAYMENT header over HTTP).Your agent only needs a wallet with a little USDC on Base — no ETH.
tools/list returns all 270)| Tool | What it does | Price (USDC) |
|---|---|---|
compress | Compress a prompt into dense language (20–40% fewer tokens) | 0.001 |
count-tokens | Estimate the token count of a text | 0.001 |
detect-language | Detect a text's language (ISO 639-1) | 0.001 |
summarize | Faithful bullet-point summary | 0.003 |
translate-to | Translate into any target language | 0.003 |
sentiment | Positive / negative / neutral + confidence | 0.002 |
entities | Named-entity recognition as JSON | 0.003 |
classify-topic | Topic classification for routing/tagging | 0.002 |
extract-json | Structured data from free text | 0.004 |
json-fix | Repair malformed JSON | 0.002 |
proofread | Spelling and grammar, same language | 0.002 |
rewrite-formal | Formal, professional rewrite | 0.003 |
moderate | Flag unsafe text | 0.002 |
injection-guard | Detect prompt-injection in text / tool outputs | 0.010 |
text-to-sql | SQL from a natural-language request | 0.005 |
regex | Regular expression from a description | 0.020 |
cron | Cron expression from a schedule in words | 0.020 |
code-review | Bugs, security issues, improvements | 0.020 |
code-gen | Code from a description | 0.008 |
read-url | Clean readable text of a web page | 0.002 |
read-pdf | Text of a PDF from a URL | 0.003 |
ocr | Text from an image or scanned PDF (EN/ES) | 0.050 |
transcribe | Speech-to-text with language detection | 0.050 |
embeddings | Embedding vector for search / RAG | 0.001 |
semantic-search | Rank documents against a query | 0.003 |
research | Web research with cited sources | 0.050 |
fact-check | Verdict + reasoning for a claim | 0.030 |
crypto-price | Live crypto price + 24h change | 0.005 |
wallet-balance | ETH and USDC balance of a Base address | 0.002 |
fx | Currency conversion quote into USDC | 0.001 |
smart-document | OCR → summary → translation, one call | 0.100 |
meeting-minutes | Recording → minutes, decisions, action items | 0.040 |
The live catalog (with the current prices, which are authoritative) is at https://pagos.andreax.dev/api/taller/peaje/catalogo.