MCP servers › io.github.gitajhd › amanchain-mcp

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

io.github.gitajhd/amanchain-mcp

59 pay-per-call AI services as MCP tools with automatic x402 USDC-on-Base payment. — the publisher's description

7 of 9 record checks metRead-only · tools listed 2026-10-23version 1.0.1TypeScriptMITstandard input/output94 tools

Summary

io.github.gitajhd/amanchain-mcp is a local MCP server listed in the official MCP registry at version 1.0.1. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 94 tools, 0 resources and 0 prompts.

Record checks

7 of 9 record checks met

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#11,090 of 15,112 packages by monthly downloads, tied with 42 others
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: local package
Transport: standard input/output
Package: npm · listed version current
License: MIT
Dependencies: no known high or critical advisories
Repository: public
Tools: 94
Described as changing data: 9 of 94 toolsAI-classified
Mainly works on: money, payments or trading; accounts and data in outside web servicesAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

9 tools are described as changing something (aman_image_gen, aman_llm_chat, aman_token_launch_check, …): our AI model's reading of the descriptions, not something we tested. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 1.0.1, published 2026-10-06 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-06 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-23
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.1 (published 2026-10-06).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

94tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: money, payments or trading; accounts and data in outside web services.

9 of 94 tools are described as changing something (creating, editing, deleting, sending or running). For 3 the reading was uncertain, so no mark is shown.

aman_token_auditreads or searches
“Token Risk Audit — Full on-chain audit of a token: collateral backing %, frozen/hidden flags, holder count, pool depth, deterministic risk flags.”
1 input
- requeststring“token symbol, e.g.”
aman_price_feedreads or searches
“AMAN Price Feed — Returns the live AMAN price from the deepest real AMM pool, with 24h change, TVL and volume.”
1 input
- requeststring“optional input — the service works without it”
aman_image_gengenerates contentdescribed as changing data
“AI Image Generation — Generate a 1024x1024 PNG image from any text prompt, returned as base64 — illustrations on demand for agent workflows.”
1 input, 1 required
- requeststringrequired“image description prompt”
aman_market_summaryreads or searches
“Market Summary — Live market snapshot: AMAN price, TVL, 24h volume, top pools with reserves and the latest executed swaps.”
1 input
- requeststring“optional input — the service works without it”
aman_crypto_pricesreads or searches
“Live Crypto Prices — Live external BTC/ETH/SOL/BNB/LTC prices (multi-source feed) plus the on-chain AMAN price and global market cap.”
1 input
- requeststring“optional input — the service works without it”
aman_swap_quote
“Swap Quote — Exact AMM quote for any pair, e.g.”
1 input, 1 required
- requeststringrequired“"100 AMAN->USDT" (amount pair)”
aman_wallet_portfolioreads or searches
“Wallet Portfolio — Complete portfolio for any address: balance, stake, LP positions, token holdings and USD valuation at live pool prices.”
1 input, 1 required
- requeststringrequired“AmanChain address”
aman_llm_chatgenerates contentdescribed as changing data
“AI Text Generation — General-purpose LLM completion for any prompt: drafting, answering, reasoning, code help — the most-requested agent capability anywhere.”
1 input, 1 required
- requeststringrequired“any prompt text”
aman_address_validatorreads or searches
“Address Validator — Validate any address across AmanChain + all bridge networks (Solana, EVM, BTC, LTC).”
1 input, 1 required
- requeststringrequired
aman_geo_ipreads or searches
“IP Geolocation — Geolocate any IP address: country, city, latitude/longitude, ASN, ISP organization and timezone.”
1 input, 1 required
- requeststringrequired“IP address, e.g.”
aman_world_clockreads or searches
“World Clock / Timezone — Exact current time for any IANA timezone with UTC offset, plus date and ISO timestamp — scheduling agents depend on it.”
1 input
- requeststring“IANA timezone, e.g.”
aman_network_statsreads or searches
“Network Statistics — Height, hashrate, supply minted/burned, staking ratio, transaction totals and mempool — all from consensus.”
1 input
- requeststring“optional input — the service works without it”

Show 82 more tools

aman_gas_trackerreads or searches
“Fee & Gas Tracker — Mempool pressure, average fees over the last 20 blocks, burn rate and congestion level.”
1 input
- requeststring“optional input — the service works without it”
aman_stable_healthreads or searches
“Stablecoin Health — Collateral backing %, redeemable supply and health flag for every on-chain stablecoin.”
1 input
- requeststring“optional input — the service works without it”
aman_supply_auditreads or searches
“Token Supply Audit — Minted, burned, max-supply headroom, holder count and issuer balance for any token (or all).”
1 input
- requeststring“token symbol or pool”
aman_token_launch_checkcreates or changes datadescribed as changing data
“Token Launch Check — Pre-flight validation of a new token against the real consensus rules — before paying the deployment fee.”
1 input
- requeststring“SYMBOL|Name|decimals|maxSupply”
aman_pool_analyticsreads or searches
“Pool Analytics — Reserves, TVL, volume, LP APR estimate and a five-size price-impact table for any pool.”
1 input
- requeststring“token symbol or pool”
aman_price_historyreads or searches
“Price History OHLC — Hourly OHLC candles built from executed swap prices over the real trading history.”
1 input
- requeststring“optional input — the service works without it”
aman_arb_scanreads or searches
“Arbitrage Spread Scan — Cross-pool implied AMAN prices with the widest spot spread — honest about slippage caveats.”
1 input
- requeststring“optional input — the service works without it”
aman_market_reportreads or searches
“Full Market Report — Composite markdown report: price, TVL, volume, pools, stablecoin health and external majors.”
1 input
- requeststring“optional input — the service works without it”
aman_holder_statsreads or searches
“Holder Distribution — Holder count, top-10 concentration, HHI index and the largest wallets for any token.”
1 input
- requeststring“token symbol or pool”
aman_staking_rewardscalculates or converts
“Staking Rewards Calculator — Projected daily/monthly/yearly rewards across the real consensus APR tiers for any amount.”
1 input, 1 required
- requeststringrequired“amount, e.g.”
aman_whale_watchreads or searches
“Whale Watch — Large-transfer scanner over real blocks — pass a threshold, e.g.”
1 input
- requeststring“threshold in AMAN, e.g.”
aman_tx_lookupreads or searches
“Transaction Lookup — Find and decode any transaction by id — status, payload, quantum-shield signature check.”
1 input, 1 required
- requeststringrequired“transaction id”
aman_block_inspectreads or searches
“Block Inspector — Full inspection of any block by height or hash — PoW facts, fees burned and tx mix.”
1 input, 1 required
- requeststringrequired“block height or hash”
aman_explorer_summaryreads or searches
“Explorer Summary — Recent blocks, transaction-type distribution, mempool size and supply effects at a glance.”
1 input
- requeststring“optional input — the service works without it”
aman_bridge_statusreads or searches
“Bridge Status — The 10 bridge networks with vault addresses, custody floats, fee and record counts.”
1 input
- requeststring“optional input — the service works without it”
aman_agent_rosterreads or searches
“Agent Roster — All registered agents with capabilities, proven call counts and volume.”
1 input
- requeststring“optional input — the service works without it”
aman_service_searchreads or searches
“Service Search — Keyword search over the live service registry — prices in AMAN and USD, ready to invoke via x402.”
1 input, 1 required
- requeststringrequired“keyword or capability”
aman_web_fetchreads or searches
“Fetch Web Page as Text — Fetch any public URL and return clean readable text with the HTML stripped — status, content-type and byte size included.”
1 input, 1 required
- requeststringrequired“public URL, e.g.”
aman_url_metareads or searches
“URL Metadata Extract — Extract a URL title, meta description, Open Graph image, canonical link and site name — link previews and scraping groundwork.”
1 input, 1 required
- requeststringrequired“public URL”
aman_web_searchreads or searches
“Live Web Search — Search the live web for any query: top results with title, URL, snippet, host and date.”
1 input, 1 required
- requeststringrequired“search query, e.g.”
aman_rss_readreads or searches
“RSS / Atom Feed Reader — Parse any RSS or Atom feed into clean items: title, link, date and summary.”
1 input, 1 required
- requeststringrequired“RSS/Atom feed URL”
aman_domain_inforeads or searches
“Domain RDAP Lookup — Registry lookup for any domain via RDAP: registrar, registration and expiry dates, nameservers and lifecycle status.”
1 input, 1 required
- requeststringrequired“domain name, e.g.”
aman_weatherreads or searches
“Weather Now + Forecast — Current weather plus a 3-day forecast for any city or lat,lon: temperature, humidity, wind and conditions (Open-Meteo live data).”
1 input, 1 required
- requeststringrequired“city or "lat,lon", e.g.”
aman_fx_ratescalculates or converts
“Fiat Exchange Rates — Live fiat FX rates: convert any amount between 30+ currencies (ECB reference data) or list rates for a base currency.”
1 input, 1 required
- requeststringrequired“"100 USD to EUR" or a base currency like "USD"”
aman_email_validatereads or searches
“Email Validation + MX — Validate an email address: syntax, real DNS MX records for the domain, and disposable-provider detection.”
1 input, 1 required
- requeststringrequired“email address”
aman_translatecalculates or converts
“Translate Text — Translate text into 20+ languages with natural quality.”
1 input, 1 required
- requeststringrequired“"ar|Hello world" (targetLang|text)”
aman_summarize
“Summarize Text or URL — Summarize any raw text or fetch a URL and return a TL;DR plus 3-5 key points — research and briefing workflows.”
1 input, 1 required
- requeststringrequired“text (80+ chars) or a URL”
aman_sentimentcalculates or converts
“Sentiment Analysis — Sentiment, polarity score, confidence and emotion labels for any text — social listening and review mining.”
1 input, 1 required
- requeststringrequired“text to analyze”
aman_keywords
“Keyword & Entity Extraction — Extract keywords, named entities and topics from any text — SEO tags, indexing and content analysis.”
1 input, 1 required
- requeststringrequired“text to analyze”
aman_crypto_pricereads or searches
“Crypto Token Price — Live USD price with 24h change for any major crypto asset (BTC, ETH, SOL, BNB, LTC, AMAN) — extended reach via CoinGecko search.”
1 input, 1 required
- requeststringrequired“symbol, e.g.”
aman_gas_pricereads or searches
“EVM Gas Price — Live gas price on Base and Ethereum mainnet in gwei with a standard-transfer USD estimate — fee timing for agents.”
1 input
- requeststring“optional: "base" or "ethereum"”
aman_evm_balancereads or searches
“EVM Wallet Balance — Native ETH balance plus USDC balance of any EVM address on Base mainnet, read live from public RPC.”
1 input, 1 required
- requeststringrequired“EVM address 0x… (Base mainnet)”
aman_ens_resolvereads or searches
“ENS Resolve — Resolve any ENS name to its Ethereum address (and reverse-resolve an address to its ENS name) with avatar when available.”
1 input, 1 required
- requeststringrequired“ENS name "name.eth" or 0x address”
aman_x402_validationreads or searches
“x402 Production Validation — Zero-spend validation of any public x402/MCP endpoint.”
1 input, 1 required
- requeststringrequired
aman_invoice_pdfgenerates contentdescribed as changing data
“Invoice PDF Generator — Standard commercial invoice PDF for agents: buyer + line items as JSON in, VAT-computed totals and a real A4 PDF (base64) out.”
1 input, 1 required
- requeststringrequired“JSON invoice: {"invoiceNumber","buyer":{"name","address"},"items":[{description,qty,unitPrice}],"vatRate","notes"}”
aman_invoice_proformagenerates contentdescribed as changing data
“Pro Forma Invoice PDF — Pro forma invoice PDF for advance payments, customs and pre-billing: real A4 document with validity date, line items and computed totals.”
1 input, 1 required
- requeststringrequired“JSON proforma: {"proformaNumber","buyer":{"name","address"},"items":[{description,qty,unitPrice}],"vatRate","validUntil","currency"}”
aman_receipt_paymentgenerates contentdescribed as changing data
“Payment Receipt PDF — Payment receipt PDF: documented proof of payment for agent transactions - payment method, transaction reference and paid date printed on a real A4 receipt.”
1 input, 1 required
- requeststringrequired“JSON receipt: {"receiptNumber","buyer":{"name"},"items":[{description,qty,unitPrice}],"payment":{"method","reference","paidOn"},"vatRate"}”
aman_credit_notegenerates contentdescribed as changing data
“Credit Note PDF — Credit note PDF for refunds and corrections against an original invoice: real A4 accounting document, negative lines supported, original invoice reference printed.”
1 input, 1 required
- requeststringrequired“JSON credit note: {"creditNoteNumber","buyer":{"name"},"originalInvoice","items":[{description,qty,unitPrice}],"vatRate"} (negative unitPrice allowed)”
aman_quote_estimategenerates contentdescribed as changing data
“Quote & Estimate PDF — Quote / estimate PDF (devis): priced offer with line items, VAT and a validity date on a real A4 document.”
1 input, 1 required
- requeststringrequired“JSON quote: {"quoteNumber","buyer":{"name","address"},"items":[{description,qty,unitPrice}],"vatRate","validUntil"}”
aman_btc_pricereads or searches
“Live btc price — Real-time Bitcoin price in USD from CoinGecko [x402 pay-per-call $0.0075/call, AmanChain, settled on-chain]”
1 input, 1 required
- requeststringrequired“crypto id like btc”
aman_crypto_price_feedreads or searches
“Crypto Price Feed B2B — Real-time crypto/USD price for agents — JSON output for trading and risk bots [x402 pay-per-call $0.0075/call, AmanChain, settled on-chain]”
1 input, 1 required
- requeststringrequired“Symbol without USDT suffix, e.g.”
aman_b2b_compliance_report
“B2B Compliance Report — Generates a compliance summary from raw transaction data for B2B audit teams.”
1 input, 1 required
- requeststringrequired“JSON object with field txs: array of {id, amount, counterparty, country}”
aman_bridge_route_checkreads or searches
“Bridge Route Check — Checks cross-chain bridge feasibility, estimated time and fees so agents route assets safely before committing funds.”
1 input, 1 required
- requeststringrequired“{"fromChain": "string", "toChain": "string", "amount": "number"}”
aman_risk_scorereads or searches
“Aman Risk Score — Scores any wallet 0-100 with flags: washTrading, flashLoanAttack, sanctionHit, mixerInteraction, exploitContract — for agent compliance checks.”
1 input, 1 required
- requeststringrequired“{"walletAddress": "string"}”
aman_crypto_whale_watchreads or searches
“Crypto Whale Watch — مراقبة حيتان السوق - تنبيه فوري عند تحركات المحافظ الكبيرة + تحليل الحيازة والحركة [x402 pay-per-call $0.0075/call, AmanChain, settled on-chain]”
1 input, 1 required
- requeststringrequired“{"walletAddress": "string"}”
aman_crypto_portfolio_trackerreads or searches
“Crypto Portfolio Tracker — Tracks any crypto wallet portfolio in real-time — returns profit/loss, allocation breakdown, and top holdings with USD values.”
1 input, 1 required
- requeststringrequired“{"walletAddress": "string"}”
aman_aml_sanctions_scanreads or searches
“AML Sanctions Screen — Screens any wallet or entity against OFAC, EU, UN sanctions lists and returns risk score + flagged matches — mandatory for B2B KYC/AML compliance.”
1 input, 1 required
- requeststringrequired“{"entity":"wallet address or company name","lists":["OFAC","EU","UN"]}”
aman_earthquakesreads or searches
“Earthquakes Near a Place — Live USGS earthquake catalog around any city or lat,lon worldwide: magnitude, depth, place, exact time and USGS event link, largest first — hazard monitoring and alerting p…”
1 input, 1 required
- requeststringrequired“city or "lat,lon" (optional "within 150km"), e.g.”
aman_weather_alertsreads or searches
“US Weather Alerts — Active watches, warnings and advisories at a US point from the National Weather Service, including those issued but not yet begun — severity, headline, affected areas and official…”
1 input, 1 required
- requeststringrequired“US city or "lat,lon", e.g.”
aman_place_geocodereads or searches
“US Address Geocoder — Resolve a US street address to its coordinates plus state, county and census tract codes (US Census Geocoder) — geo-enrichment groundwork for agents.”
1 input, 1 required
- requeststringrequired“US street address, e.g.”
aman_place_permitsreads or searches
“Building Permits Lookup — Recorded building permits at an exact site address in Chicago or New York City (official city open-data portals): permit type, status, dates, work description and declared v…”
1 input, 1 required
- requeststringrequired“"chicago|<street address>" or "nyc|<street address> <borough>"”
aman_vehicle_vinreads or searches
“VIN Decoder — Decode a 17-character VIN into make, model, year, body class, engine, fuel, transmission, plant and safety equipment (NHTSA vPIC) — the standard vehicle-identification call.”
1 input, 1 required
- requeststringrequired“17-character VIN, e.g.”
aman_vehicle_recallsreads or searches
“Vehicle Safety Recalls — Safety recalls issued for a make/model/year (NHTSA): campaign number, component, summary, consequence and remedy, newest first.”
1 input, 1 required
- requeststringrequired“"make|model|year", e.g.”
aman_vehicle_complaintsreads or searches
“Vehicle Owner Complaints — Owner-filed safety complaints for a make/model/year (NHTSA) with crash/fire/injury/death tallies, top components and the newest complaint summaries.”
1 input, 1 required
- requeststringrequired“"make|model|year", e.g.”
aman_company_filingsreads or searches
“SEC Company Filings — Look up a US public company by ticker or name (SEC EDGAR): registry identity, SIC industry, filer category and recent filings with form type, date and document link — diligence …”
1 input, 1 required
- requeststringrequired“ticker or company name, e.g.”
aman_federal_awardsreads or searches
“US Federal Awards — Federal contracts and grants held by a recipient, largest first (USAspending.gov): award ID, amount, period, agency — competitive-intel and vendor screening.”
1 input, 1 required
- requeststringrequired“recipient name, e.g.”
aman_legal_entitiesreads or searches
“Legal Entity (LEI) Lookup — Search the global GLEIF registry by legal name or 20-character LEI: entity status, category, jurisdiction, headquarters address and registration lifecycle — counterparty v…”
1 input, 1 required
- requeststringrequired“legal name or LEI, e.g.”
aman_company_profilereads or searches
“Company Profile from Domain — Enrich a company domain: site title, description, contact emails, social profiles plus registry registration data (registrar, dates, nameservers) from live RDAP — lead-s…”
1 input, 1 required
- requeststringrequired“domain, e.g.”
aman_commerce_searchreads or searches
“Product Search (E-commerce) — Search the live web for a product across major e-commerce merchants: normalized results with merchant flag and price extracted from listings where published.”
1 input, 1 required
- requeststringrequired“product query, e.g.”
aman_email_sendsends messagesdescribed as changing data
“Send Email — Transactional email delivery from the node: to|subject|body — sent through the platform mail relay (Resend).”
1 input, 1 required
- requeststringrequired“"to@example.com|Subject|Message body"”
aman_web_readreads or searches
“Read Web Page (Markdown) — Read any public web page and extract its content as clean structured markdown (headings, links, lists, images with resolved URLs) plus metadata — the agent-native reader.”
1 input, 1 required
- requeststringrequired“public URL, e.g.”
aman_research
“Deep Research with Sources — Deep research on any topic: live search, full-text extraction from the top 5 sources, then a synthesized analyst brief with key findings and numbered citations.”
1 input, 1 required
- requeststringrequired“research topic, e.g.”
aman_fx_historyreads or searches
“FX Rate History — Historical ECB reference exchange rates for any pair over a date range: full daily series plus min, max, average and percentage change computed for you — backtesting and reporting.”
1 input, 1 required
- requeststringrequired“"USD/EUR|2026-09-01|2026-09-30" or "USD/MAD|30" for the last 30 days”
aman_stock_quotereads or searches
“Stock Quote — Live stock quote for any listed ticker (Yahoo Finance): price, previous close, change percent, day range and the last daily closes — equity snapshots for agents.”
1 input, 1 required
- requeststringrequired“ticker symbol, e.g.”
aman_crypto_tickerreads or searches
“Crypto 24h Ticker (Binance) — Exchange-grade 24-hour stats for any Binance spot pair: last price, change percent, high/low, volumes, weighted average and bid/ask — deeper than a price check.”
1 input, 1 required
- requeststringrequired“pair or asset, e.g.”
aman_defi_yieldsreads or searches
“DeFi Yields & Interest Rates — Current lending and farming yields across DeFi (DeFiLlama): APY per pool by asset or protocol, average APY computed over matches, TVL-ranked — yield-scanning groundwork.”
1 input, 1 required
- requeststringrequired“asset or protocol, e.g.”
aman_hn_newsreads or searches
“Hacker News Search — Story search across Hacker News (Algolia API): titles, points, comment counts, authors and canonical discussion links — tech-signal monitoring.”
1 input, 1 required
- requeststringrequired“search query, e.g.”
aman_app_lookupreads or searches
“App Store Lookup — Search the Apple App Store for apps by keyword: name, developer, price, rating and rating count, genre, bundle id and store link — app-intelligence groundwork.”
1 input, 1 required
- requeststringrequired“app name or keyword, e.g.”
aman_holidaysreads or searches
“Public Holidays — Official public-holiday calendar for any country and year (Nager.Date): dates, local and English names, plus the next upcoming holiday with days remaining — scheduling pipelines.”
1 input, 1 required
- requeststringrequired“country code and optional year, e.g.”
aman_air_qualityreads or searches
“Air Quality Report — Current air quality at any city or coordinate (Open-Meteo/CAMS): PM2.5, PM10, US and European AQI, pollutant breakdown, dominant pollutant and a plain-language health band.”
1 input, 1 required
- requeststringrequired“city or "lat,lon", e.g.”
aman_dns_lookupreads or searches
“DNS Record Lookup — Resolve A, AAAA, CNAME, MX, TXT, NS, SOA, SRV or CAA records for any domain via Google Public DNS (DoH) — infrastructure and deliverability checks.”
1 input, 1 required
- requeststringrequired“"example.com MX" or just "example.com" (default type A)”
aman_endpoint_checkreads or searches
“x402 Endpoint Check — Zero-spend health probe of any public x402 API: /, /health, /.well-known/x402.json and x402list.txt reachability with latencies, optional 402 quote-shape inspection (payTo prese…”
1 input, 1 required
- requeststringrequired“public URL, e.g.”
aman_token_deep_reportreads or searches
“Token Deep Report — One-call composite for any asset: Binance 24h stats (price, range, volumes, trades) joined with the live DeFi yield landscape for the same asset (top pools, average APY) and a rea…”
1 input, 1 required
- requeststringrequired“asset or pair, e.g.”
aman_market_session_briefreads or searches
“Market Session Brief — The whole session picture in one call: six majors from Binance, our AMAN price from real AMM reserves, and top stablecoin yields with average APY — delivered as data plus a mar…”
1 input
- requeststring“optional focus: "majors", "defi", or empty for all”
aman_market_moversreads or searches
“24h Market Movers — Ranked 24h movers across a fixed 18-pair liquid universe: top gainers, worst losers and the flattest books, with volumes — momentum screening without a dozen calls.”
1 input
- requeststring“optional top-N, e.g.”
aman_yield_top_tablereads or searches
“Top Yields Table — Top-N DeFi pools filtered by asset and stability (DeFiLlama): TVL-ranked table, average APY and a projected yearly income on a 10k notional — yield scanning with the cache age disc…”
1 input
- requeststring“"USDC|10|stable" — asset|limit|mode (stable or all)”
aman_fx_daily_digestreads or searches
“FX Daily Digest — ECB reference digest for any base currency: up to 12 pairs with the live rate, 7-day percentage change and weekly min–max — reporting-ready markdown included.”
1 input
- requeststring“base currency, e.g.”
aman_multi_price_boardreads or searches
“Multi-Price Board — Up to 12 assets priced in ONE call (Binance 24h stats) plus our on-chain AMAN price from real AMM reserves — with a markdown board.”
1 input
- requeststring“optional comma assets, e.g.”
aman_funding_ratesreads or searches
“Multi-Venue Funding Rates — Perpetual funding rates for any major asset across Binance futures, Bybit linear and OKX swaps: raw 8h rate, annualized equivalent, mark/index price, next funding time and…”
1 input, 1 required
- requeststringrequired“asset or comma pairs, e.g.”
aman_csv_preflightcalculates or converts
“CSV Preflight — Structural quality report for your CSV before machines consume it: delimiter sniffing, RFC-4180 quote-aware parsing, duplicate headers, ragged rows, empty-cell ratios, per-column type…”
1 input, 1 required
- requeststringrequired“raw CSV text with a header row, e.g.”
aman_stock_screenreads or searches
“Daily Stock Screen — Ranked US equity board over a disclosed 24-ticker liquid universe: top gainers, losers or volume leaders with market breadth (advancers/decliners, average change, tone) and 52-we…”
1 input
- requeststring“optional mode: "gainers" (default), "losers", "volume" or "levels"”
amanchain_catalogreads or searches
“Browse the live AmanChain x402 catalog: 92 pay-per-call services with prices, categories and input formats.”
1 input
- categorystring“optional filter, e.g.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 94 tools
Says what it returns: 100% of 94 tools
States limits, defaults or errors: 24% of 54 tools
Says when to use it: 100% of 54 tools
Items covered per tool: 3.2 of 4 on average

Counted from the listing

Parameters with a description: 98% of 94
Tools with a description: 100% of 94
Typical description length: 219 characters

The tool set

Counted from the listing

Tools: 94
Size of the list: about 10,642 tokens for an agent to load (characters ÷ 4)
Naming: 94 of 94 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 94 of 94 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package amanchain-mcp

Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "amanchain-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "amanchain-mcp@1.0.1"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "amanchain-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "amanchain-mcp@1.0.1"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "amanchain-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "amanchain-mcp@1.0.1"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"amanchain-mcp","type":"stdio","command":"npx","args":["-y","amanchain-mcp@1.0.1"]}'

Claude Code

claude mcp add --transport stdio amanchain-mcp -- npx -y amanchain-mcp@1.0.1

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y amanchain-mcp@1.0.1

This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 1.0.1
Latest stable: 1.0.1
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-23 (npm audit). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-FlWiiwQ27bNDWScWH…
Signature: signed
License: MIT

Source: the package registry · 2026-10-23.

Usage

Downloads: 166 in the last month

Source: api.npmjs.org · 2026-10-23.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 1.0.1 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/gitajhd/amanchain-mcp	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.gitajhd · 2 servers
GitHub owner: a personal account (gitajhd)
Build record: signed

Repository: github.com/gitajhd/amanchain-mcp
Stars: 0
Repository age: 0–30 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

7 of 9 record checks met

#11,090 of 15,112 packages by monthly downloads, tied with 42 others
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.gitajhd/amanchain-mcp

Answered from the data above

Is io.github.gitajhd/amanchain-mcp safe to install?

We do not rate servers as safe or unsafe. 7 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 9 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has io.github.gitajhd/amanchain-mcp been security tested?

Partly. 2 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.gitajhd/amanchain-mcp do?

It lists 94 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, send messages, generate content and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.gitajhd/amanchain-mcp change or delete data?

9 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does io.github.gitajhd/amanchain-mcp publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 1.0.1, the latest stable release on npm.

Where is the source code of io.github.gitajhd/amanchain-mcp?

In github.com/gitajhd/amanchain-mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: not run · nothing to check it against
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

2 exercised10 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted the published package in an isolated sandbox (read-only mode)
17,879 msConnected after 0 redirects.
Read the inventory: 94 tools, 0 resources, 0 prompts.
19,438 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

no value

No value: the two AI models (Gemini and Claude) disagreed, so neither answer is shown.

Pricing modelAI-classified

no value

The website listed in the registry is a code-hosting, package or marketplace page, not the product's own site.

Programming language

TypeScript

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sri)

package registry · 2026-10-23

Signature / provenance

signed

package registry · 2026-10-23

Dependency advisories

none known

npm audit · 2026-10-23

Popularity

166 downloads a month

package registry · 2026-10-23

Publisher signals

owner: a personal account · repository age: 0–30 days · stars: 0–9 · build record: signed

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

your machine

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.gitajhd/amanchain-mcp: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.gitajhd/amanchain-mcp

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.gitajhd/amanchain-mcp)](https://protocolprobe.com/mcp/servers/io.github.gitajhd/amanchain-mcp)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology