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.

onchaincheck

REMOTE · ONCHAINCHECK.DEV

100+ pay-per-call tools: token risk, wallet sanctions screening, onchain data, web, company, AI

Available components

+2 this week 64 Trust /100

Last scanned (14 hours ago)

Scores higher than 46% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Crypto and Web3

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 Security46
Transport & Reachability100
Schema Quality & AI Usability67
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 23428 tokens (~153/item across 153 items; 153 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 Management43
  • Stability observed for 13 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 153 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 153 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 (11)

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

Checks we could not complete (2)

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 153 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.

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.

  • 21 Nov 26 0
    • New tool “prepayment_safety_check_lite_batch” functional
  • 20 Nov 26 0
    • A breaking change shipped without a version bump: still 1.0.0 ▼ security
    • Tool “prepayment_safety_check” rewrote its description, which is the text the model reads security
    • Tool “prepayment_safety_check_lite” rewrote its description, which is the text the model reads security
    • Schema quality: 138 → 152 ▼ functional
    • “chat_completions” changed the type of “max_tokens”: string → number|string ▼ functional
    • “chat_completions” changed the type of “stream”: string → boolean|string ▼ functional
    • “chat_completions” changed the type of “temperature”: string → number|string ▼ functional
    • New tool “perps_funding” functional
    • New tool “pii_redact” functional
    • New tool “address_label” functional
    • New tool “agent_access_check” functional
    • New tool “airport_status” functional
    • New tool “brazil_markets” functional
    • New tool “central_bank_rates” functional
    • New tool “clinical_trials_search” functional
    • New tool “companies_hiring_scan” functional
    • New tool “crypto_candles” functional
    • New tool “crypto_fear_greed” functional
    • New tool “crypto_market_brief” functional
    • New tool “defi_tvl” functional
    • New tool “defi_yields” functional
    • New tool “drug_safety” functional
    • New tool “economic_calendar” functional
    • New tool “extract_tables” functional
    • New tool “federal_register_search” functional
    • New tool “fund_holdings” functional
    • New tool “gas_compare” functional
    • New tool “package_check” functional
    • New tool “packages_check” functional
    • New tool “prompt_injection_check” functional
    • New tool “rerank_documents” functional
    • New tool “sec_13f_holdings” functional
    • New tool “sec_8k_events” functional
    • New tool “sec_insider_trades” functional
    • New tool “stablecoin_market” functional
    • New tool “ukraine_markets” functional
    • New tool “us_address_geocode” functional
    • New tool “us_airport_delays” functional
    • New tool “us_rates” functional
    • New tool “us_recall_search” functional
    • New tool “web_check” functional
    • New tool “wiki_lookup” functional
    • New tool “wikipedia_trending” functional
    • New tool “x402_recommend_api” functional
    • “prepayment_safety_check” reworded the description of “chain” cosmetic
    • “prepayment_safety_check_lite” reworded the description of “chain” cosmetic
  • 19 Nov 26 +1
    • Tool “company_jobs” rewrote its description, which is the text the model reads security
  • 18 Nov 26 0
    • Tool “token_quick_check” rewrote its description, which is the text the model reads security
    • Tool “token_risk_check” rewrote its description, which is the text the model reads security
    • Tool “token_watchlist” rewrote its description, which is the text the model reads security
  • 16 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 0
    • New tool “company_hiring_movers” functional
  • 14 Nov 26 +1
    • Tool “ai_chat” rewrote its description, which is the text the model reads security
    • Tool “ai_chat_pro” rewrote its description, which is the text the model reads security
    • Tool “ai_text_to_speech” rewrote its description, which is the text the model reads security
    • Tool “chat_completions” rewrote its description, which is the text the model reads security
    • New tool “token_quick_check” functional
    • “ai_text_to_speech” reworded the description of “text” cosmetic
  • 12 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.

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://onchaincheck.dev/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=onchaincheck.dev CN=WE1,O=Google Trust Services,C=US 24 Oct 2026 22 Jan 2027 ECDSA 256 ECDSA-SHA256 922cf79c9652f3b70edb08a33c298bb9
SANs: onchaincheck.dev, testnet.onchaincheck.dev, *.testnet.onchaincheck.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 onchaincheck.dev. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
dev. DS published 60074 8 Verified
onchaincheck.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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://onchaincheck.dev/mcp Verified 200
http (plaintext) http://onchaincheck.dev/mcp Inconclusive 406
MCP tools · 153 exposed · ~23,428 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
address_label ~162

What is this address? For 1-10 addresses on Ethereum, Base, Arbitrum, Optimism or Polygon: wallet, contract or EIP-7702 delegated wallet; the verified contract name and proxy implementation (Sourcify); a category such as mixer (Tornado Cash), privacy protocol, DEX router, bridge, Safe multisig, smart wallet, lending, token or stablecoin; ERC-20 details, OFAC SDN status, native balance and flags. Wallets get no owner name. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstring–One address
addressesstring–Or up to 10, comma-separated
chainstring–Chain (default eth)

No output schema declared.

No examples provided.

address_sanctions_exposure ~135

Has this wallet dealt with sanctioned addresses? Reads up to 4,000 of the wallet's latest transfers (native, internal, ERC-20, NFTs) on Base, Ethereum, Arbitrum, Optimism or Polygon and checks every counterparty against the OFAC SDN list's addresses: each sanctioned counterparty with entity, programs, direction, transfer count, assets and dates. Direct exposure only. Not legal advice. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstringyesEVM wallet address
chainstring–Chain to scan (default base)

No output schema declared.

No examples provided.

address_sanctions_screen ~199

Is this address sanctioned? Screens a crypto address against the US Treasury OFAC SDN list's published digital currency addresses (ETH, USDC, USDT, XBT, SOL, TRX and others): the listed entity, programs and listing date on a match, or not found as of the list date. Adds whether it is a wallet (EOA) or contract on Base, Ethereum, Arbitrum, Optimism or Polygon, or a wallet or program-derived address on Solana. Not legal advice. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
addressstringyesAddress to screen: 0x (EVM), base58 (Solana), or any other currency's address with chain=other
chainstring–Chain for the wallet/contract check; defaults to base for 0x addresses, solana for Solana addresses, otherwise other (list check only)

No output schema declared.

No examples provided.

agent_access_check ~149

May an agent fetch and use this URL? robots.txt applied per RFC 9309 to your user agent and to 12 AI crawlers and fetchers (GPTBot, ClaudeBot, Google-Extended...), crawl-delay, X-Robots-Tag and meta robots, noai and TDM reservation opt-outs, redirects and x402. Plus agent readiness, scored 0-100: llms.txt, MCP server card, A2A agent card, OpenAPI, sitemap. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
agentstring–robots.txt product token to check for (default *)
urlstringyesPage URL or domain to check

No output schema declared.

No examples provided.

ai_chat ~211

LLM chat completion, flat $0.003 a call: send a prompt (plus optional system) or an OpenAI-style messages array and get the reply text with token usage. Models: gpt-oss-20b (default), gemma-4-26b, glm-4.7-flash, llama-4-scout. Up to 16,000 characters in and 1,024 tokens out; json=true for JSON output. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
jsonstring–true asks for a single JSON object
max_tokensstring–Most tokens to generate, up to 1024
modelstring–Model (default gpt-oss-20b)
promptstring–The user message (or send an OpenAI-style messages array instead)
systemstring–Optional system instructions
temperaturestring–0 to 2 (default 0.6)

No output schema declared.

No examples provided.

ai_chat_pro ~217

LLM chat completion on larger models, flat $0.01 a call: prompt (plus optional system) or an OpenAI-style messages array in, reply text and token usage out. Models: gpt-oss-120b (default), deepseek-v4.1-flash, llama-3.3-70b, mistral-small-3.1. Up to 32,000 characters in and 2,048 tokens out; json=true for JSON output. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
jsonstring–true asks for a single JSON object
max_tokensstring–Most tokens to generate, up to 2048
modelstring–Model (default gpt-oss-120b)
promptstring–The user message (or send an OpenAI-style messages array instead)
systemstring–Optional system instructions
temperaturestring–0 to 2 (default 0.6)

No output schema declared.

No examples provided.

ai_embeddings ~93

Text embeddings with bge-m3 (1,024 dimensions, multilingual): one text, or up to 32 texts in one call (POST texts array), up to 32,000 characters in all. For semantic search, clustering and similarity. Costs $0.002 USDC on Base via x402.

NameTypeReqDescription
textstring–Text to embed (or texts: an array of up to 32 strings)

No output schema declared.

No examples provided.

ai_image ~120

Generate an image from a text prompt with FLUX.1 [schnell]: a 1024x1024 JPEG returned as base64 in JSON. Optional steps (1-8, default 4) and seed for repeatable results. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
promptstringyesWhat to draw, up to 1,000 characters
seedstring–Seed for a repeatable image
stepsstring–Diffusion steps 1-8 (default 4)

No output schema declared.

No examples provided.

ai_keywords ~95

Keywords with relevance scores (up to 10), named entities typed as person, organization, location, product or event (up to 10), and 1-3 broad topics from a text. Up to 5,000 characters. Llama 4 Scout on Workers AI. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
textstringyesThe text, up to 5,000 characters

No output schema declared.

No examples provided.

ai_rewrite ~104

Rewrite a text in another tone, keeping its meaning, facts and language: professional (default), casual, friendly, formal, concise, simple, persuasive, confident or empathetic. Up to 5,000 characters. Llama 4 Scout on Workers AI. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
stylestring–Target tone (default professional)
textstringyesThe text, up to 5,000 characters

No output schema declared.

No examples provided.

ai_sentiment ~104

Sentiment of a text (review, post, email, support ticket): positive, negative, neutral or mixed, a score from -1 to 1, confidence, up to 3 emotions and per-aspect sentiment. Up to 5,000 characters, any language. Llama 4 Scout on Workers AI. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
textstringyesThe text, up to 5,000 characters

No output schema declared.

No examples provided.

ai_summarize ~119

Summary of a text in one sentence, 2-3 sentences or a paragraph (length short, medium or long), plus 3-5 key points and the text's language. Up to 5,000 characters. Llama 4 Scout on Workers AI. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
lengthstring–short (1 sentence), medium (2-3, default) or long (a paragraph)
textstringyesThe text, up to 5,000 characters

No output schema declared.

No examples provided.

ai_text_to_speech ~104

Text to speech: English (up to 600 characters, Deepgram Aura 1) or Spanish (up to 300, Deepgram Aura 2) spoken as an MP3 file, returned as base64 in JSON. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
langstring–Language (default en)
textstringyesText to speak: up to 600 characters in English, 300 in Spanish

No output schema declared.

No examples provided.

ai_transcribe ~110

Speech to text with Whisper large-v3 turbo: pass the URL of an audio file (MP3, WAV, OGG, M4A; up to 15 MB) and get the transcript, detected language, duration, word count and timed segments. Optional language hint. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
languagestring–Two-letter language hint (en, fr); detected when omitted
urlstringyesPublic URL of the audio file

No output schema declared.

No examples provided.

ai_translate ~103

Translate text between 100 languages (m2m100): up to 5,000 characters, target language as an ISO 639-1 code; the source language is detected when not given. Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
fromstring–Source language; detected when omitted
textstringyesText to translate
tostringyesTarget language (fr, es, de, ja, zh...)

No output schema declared.

No examples provided.

airport_status ~155

One airport in one call, by IATA or ICAO code: name, location and runways; live FAA status for US airports (ground stops, ground delay programs, arrival and departure delays, closures); the latest METAR and the TAF forecast, decoded (wind, gusts, visibility, clouds, weather, flight category VFR/MVFR/IFR/LIFR per period); and flags such as ground-stop or ifr. Data: aviationweather.gov (NOAA) and FAA NAS status. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
airportstringyesIATA (JFK, LHR) or ICAO (KJFK, EGLL) airport code

No output schema declared.

No examples provided.

arbitrum_contract_info ~108

Identify what lives at a Arbitrum One address: wallet (EOA, including EIP-7702 delegation) or contract, which token standard it implements (ERC-20, ERC-721, ERC-1155), name and symbol, upgradeable-proxy implementation and admin, smart-wallet proxies, bytecode size, nonce and ETH balance. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
addressstringyesAny address on Arbitrum One

No output schema declared.

No examples provided.

arbitrum_erc20_allowance ~106

ERC-20 allowance on Arbitrum One: how much a spender may transfer from an owner, whether the approval is effectively unlimited, the owner's balance, and the amount the spender could move right now. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
ownerstringyesAddress that granted the approval
spenderstringyesAddress allowed to spend
tokenstringyesERC-20 contract on Arbitrum One

No output schema declared.

No examples provided.

arbitrum_gas_prices ~99

Current Arbitrum One gas conditions: block number, base fee, gas price and priority fee in gwei, and the estimated cost in ETH and USD of a native transfer and an ERC-20 transfer (Chainlink ETH/USD); plus how the current price ranks against our own samples every 10 minutes over the last 7 days, and the usually cheapest UTC hour. Costs $0.005 USDC on Base via x402.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

arbitrum_large_trades ~232

Whale and large-trade tracker for an ERC-20 on Arbitrum One: every buy and sell in the last N minutes on the token's deepest WETH/USDC pools (Uniswap v3), with USD size, side, wallet and transaction for the largest trades, buy/sell volume and net flow, and the wallets that bought or sold the most; plus the token's launch from our history (first-sight risk score, liquidity after 24 h/7 d/30 d, deployer record) when we recorded it. Costs $0.02 USDC on Base via x402.

NameTypeReqDescription
limitstring–Max trades listed, 1 to 40, default 20
minUsdstring–Only list trades at least this large in USD, default 1000
minutesstring–Look-back window in minutes; 5 to 240, default 60 (capped at 12,000 blocks, about 50 minutes on Arbitrum)
tokenstringyesToken contract address on Arbitrum One

No output schema declared.

No examples provided.

arbitrum_new_pools ~192

New trading pools created on Arbitrum One in the last N minutes on Uniswap v4, Uniswap v2, Uniswap v3: both tokens with symbol, name and decimals, fee tier, v4 hooks, whether it pairs with ETH, WETH or USDC, and quote liquidity where readable; plus, from our launch history, each pool's first-sight risk score and how many new pools on its venue lost their liquidity within 24 h. Unvetted: many new pools are spam. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
limitstring–Max pools listed, newest first, 1 to 50, default 25
minutesstring–Look-back window in minutes; 5 to 240, default 60 (capped at 12,000 blocks, about 50 minutes on Arbitrum)

No output schema declared.

No examples provided.

arbitrum_nft_metadata ~114

Metadata for an ERC-721 or ERC-1155 token on Arbitrum One: collection name, current owner (ERC-721), token URI, and the metadata JSON fetched and decoded from IPFS, Arweave, HTTPS or an inline data URI, with a browser-loadable image URL. Costs $0.008 USDC on Base via x402.

NameTypeReqDescription
contractstringyesNFT collection contract on Arbitrum One
tokenIdstringyesToken id as a decimal string

No output schema declared.

No examples provided.

arbitrum_token_snapshot ~140

Rug check and due-diligence snapshot of an ERC-20 token on Arbitrum One: a 0-100 risk score with reasons, name, symbol, decimals, supply, owner and whether ownership is renounced, upgradeable-proxy detection, owner-only functions found in the bytecode (mint, pause, blacklist, fee changes), and USD price, liquidity and FDV from the deepest WETH or USDC pool on Uniswap v3. Facts only, no buy or sell opinion. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstringyesToken contract address on Arbitrum One

No output schema declared.

No examples provided.

arbitrum_transaction_summary ~81

Human-readable summary of a Arbitrum One transaction: status, block and time, sender and recipient, ETH value, gas used and fee, method selector, and decoded ERC-20 transfers with token symbols and amounts. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
hashstringyesTransaction hash on Arbitrum One

No output schema declared.

No examples provided.

arbitrum_wallet_balances ~105

Native ETH balance of a Arbitrum One wallet plus the balances of up to 20 ERC-20 tokens you list, formatted with each token's symbol and decimals, read live from Arbitrum One. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
addressstringyesWallet address on Arbitrum One
tokensstring–Comma-separated ERC-20 contract addresses on Arbitrum One, up to 20

No output schema declared.

No examples provided.

arbitrum_wallet_profile ~137

Who is this Arbitrum One address? Wallet age (first transfer), first funder, contract or EOA, ETH balance and nonce, the latest transfers in and out (native, ERC-20, NFTs), top counterparties by count, and recent large transfers in USD (ETH, WETH, USDC, USDT), from Alchemy's transfer index; plus, from our launch history, tokens it deployed and how many lost their liquidity, and deployers it funded. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstringyesWallet or contract address on Arbitrum One

No output schema declared.

No examples provided.

base_contract_info ~101

Identify what lives at a Base address: wallet (EOA, including EIP-7702 delegation) or contract, which token standard it implements (ERC-20, ERC-721, ERC-1155), name and symbol, upgradeable-proxy implementation and admin, smart-wallet proxies, bytecode size, nonce and ETH balance. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
addressstringyesAny address on Base

No output schema declared.

No examples provided.

base_erc20_allowance ~99

ERC-20 allowance on Base: how much a spender may transfer from an owner, whether the approval is effectively unlimited, the owner's balance, and the amount the spender could move right now. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
ownerstringyesAddress that granted the approval
spenderstringyesAddress allowed to spend
tokenstringyesERC-20 contract on Base

No output schema declared.

No examples provided.

base_gas_prices ~95

Current Base gas conditions: block number, base fee, gas price and priority fee in gwei, and the estimated cost in ETH and USD of a native transfer and an ERC-20 transfer (Chainlink ETH/USD); plus how the current price ranks against our own samples every 10 minutes over the last 7 days, and the usually cheapest UTC hour. Costs $0.005 USDC on Base via x402.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

base_large_trades ~229

Whale and large-trade tracker for an ERC-20 on Base: every buy and sell in the last N minutes on the token's deepest WETH/USDC pools (Uniswap v3 or Aerodrome), with USD size, side, wallet and transaction for the largest trades, buy/sell volume and net flow, and the wallets that bought or sold the most; plus the token's launch from our history (first-sight risk score, liquidity after 24 h/7 d/30 d, deployer record) when we recorded it. Costs $0.02 USDC on Base via x402.

NameTypeReqDescription
limitstring–Max trades listed, 1 to 40, default 20
minUsdstring–Only list trades at least this large in USD, default 1000
minutesstring–Look-back window in minutes; 5 to 240, default 60 (capped at 12,000 blocks, about 50 minutes on Arbitrum)
tokenstringyesToken contract address on Base

No output schema declared.

No examples provided.

base_new_pools ~192

New trading pools created on Base in the last N minutes on Uniswap v4, Uniswap v2, Uniswap v3 or Aerodrome: both tokens with symbol, name and decimals, fee tier, v4 hooks, whether it pairs with ETH, WETH or USDC, and quote liquidity where readable; plus, from our launch history, each pool's first-sight risk score and how many new pools on its venue lost their liquidity within 24 h. Unvetted: many new pools are spam. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
limitstring–Max pools listed, newest first, 1 to 50, default 25
minutesstring–Look-back window in minutes; 5 to 240, default 60 (capped at 12,000 blocks, about 50 minutes on Arbitrum)

No output schema declared.

No examples provided.

base_nft_metadata ~107

Metadata for an ERC-721 or ERC-1155 token on Base: collection name, current owner (ERC-721), token URI, and the metadata JSON fetched and decoded from IPFS, Arweave, HTTPS or an inline data URI, with a browser-loadable image URL. Costs $0.008 USDC on Base via x402.

NameTypeReqDescription
contractstringyesNFT collection contract on Base
tokenIdstringyesToken id as a decimal string

No output schema declared.

No examples provided.

base_resolve_basename ~79

Resolve a Basename (name.base.eth) to its Base address and profile records (avatar, description, url, Twitter, GitHub). Accepts "jesse", "jesse.base" or "jesse.base.eth". Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
namestringyesBasename

No output schema declared.

No examples provided.

base_token_snapshot ~137

Rug check and due-diligence snapshot of an ERC-20 token on Base: a 0-100 risk score with reasons, name, symbol, decimals, supply, owner and whether ownership is renounced, upgradeable-proxy detection, owner-only functions found in the bytecode (mint, pause, blacklist, fee changes), and USD price, liquidity and FDV from the deepest WETH or USDC pool on Uniswap v3 or Aerodrome. Facts only, no buy or sell opinion. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstringyesToken contract address on Base

No output schema declared.

No examples provided.

base_transaction_summary ~74

Human-readable summary of a Base transaction: status, block and time, sender and recipient, ETH value, gas used and fee, method selector, and decoded ERC-20 transfers with token symbols and amounts. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
hashstringyesTransaction hash on Base

No output schema declared.

No examples provided.

base_wallet_balances ~92

Native ETH balance of a Base wallet plus the balances of up to 20 ERC-20 tokens you list, formatted with each token's symbol and decimals, read live from Base. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
addressstringyesWallet address on Base
tokensstring–Comma-separated ERC-20 contract addresses on Base, up to 20

No output schema declared.

No examples provided.

base_wallet_profile ~130

Who is this Base address? Wallet age (first transfer), first funder, contract or EOA, ETH balance and nonce, the latest transfers in and out (native, ERC-20, NFTs), top counterparties by count, and recent large transfers in USD (ETH, WETH, USDC, USDT), from Alchemy's transfer index; plus, from our launch history, tokens it deployed and how many lost their liquidity, and deployers it funded. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
addressstringyesWallet or contract address on Base

No output schema declared.

No examples provided.

brazil_markets ~184

Brazil's official market numbers in one call, from Banco Central do Brasil: PTAX exchange rates (closing buy and sell, 1-day and 1-week change, intraday bulletin) for USD, EUR and up to 5 currencies; Selic target with its last change, effective Selic, CDI and the real rate; IPCA and IGP-M inflation (month and 12-month); Focus survey medians for IPCA, Selic, GDP and USD/BRL; and the bank-holiday calendar (business day today, next one, D+2). Costs $0.003 USDC on Base via x402.

NameTypeReqDescription
currencystring–PTAX currencies, comma-separated, up to 5: USD, EUR, GBP, JPY, CHF, CAD, AUD, DKK, NOK, SEK (default USD,EUR)

No output schema declared.

No examples provided.

canada_business_days ~119

Number of business days between two dates in a Canadian province or territory, excluding weekends and that province's statutory holidays (with weekend holidays moved to their observed weekday). Counts from the start date up to but not including the end date, and lists the holidays skipped. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
fromstringyesFirst day counted, YYYY-MM-DD
provincestringyesTwo-letter Canadian province or territory code
tostringyesDay after the last day counted, YYYY-MM-DD

No output schema declared.

No examples provided.

canada_sales_tax ~138

Canadian sales tax breakdown for an amount in a province or territory: GST, HST, PST, RST or QST with each rate and amount rounded to the cent, plus the total. Rates are looked up for the given date (default today), so historical changes such as Nova Scotia's 2025 HST cut are handled. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
amountstringyesPre-tax amount in CAD
datestring–Date the rates apply to, YYYY-MM-DD; defaults to today (UTC)
provincestringyesTwo-letter Canadian province or territory code

No output schema declared.

No examples provided.

canada_statutory_holidays ~97

Statutory (general) holidays for a Canadian province or territory in a given year, using the province's local names, with the actual date and the weekday it is observed when it falls on a weekend. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
provincestringyesTwo-letter Canadian province or territory code
yearstringyesYear from 2000 to 2100

No output schema declared.

No examples provided.

central_bank_rates ~179

Central bank policy rates from each bank's own data feed: Fed, ECB, Bank of England, Bank of Canada, Riksbank, Norges Bank, Danmarks Nationalbank and Banco Central do Brasil. Per bank: current rate, last change (date, from, to, bps), 12-month change and stance (hiking, cutting, on hold). Plus an FX carry ranking against a funding currency: rate differential, spot and 1-month spot move from ECB reference rates. Refreshed hourly. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
currencystring–Comma-separated subset: USD, EUR, GBP, CAD, SEK, NOK, DKK, BRL (default all)
funderstring–Funding currency for the carry ranking (default: the lowest-rate currency)

No output schema declared.

No examples provided.

chat_completions ~211

OpenAI-compatible chat completions, flat $0.002 a call: the same request and response as OpenAI's /v1/chat/completions (messages, model, max_tokens, temperature, response_format json_object, stream), so an OpenAI SDK works by changing the base URL. Models: llama-4-scout (default), gpt-oss-20b, gemma-4-26b, glm-4.7-flash. Up to 10,000 characters in, 1,024 tokens out. Costs $0.002 USDC on Base via x402.

NameTypeReqDescription
max_tokensnumber|string–Most tokens to generate (above 1,024 is capped)
messagesarrayyesOpenAI-style messages
modelstring–Model (default llama-4-scout; other names run on the default)
streamboolean|string–true answers as Server-Sent Events chunks
temperaturenumber|string––

No output schema declared.

No examples provided.

clinical_trials_search ~278

Search ClinicalTrials.gov by condition, drug or intervention, sponsor or words, filtered by status (open by default), phase and country; or give an NCT id for one study with its full eligibility criteria. Each study: status, phases, sponsor, enrollment, age and sex limits, dates, primary outcomes, site count by country and sites in the country asked. Up to 20 per call, most recently updated first. Data: US National Library of Medicine. Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
conditionstring–Disease or condition (glioblastoma, type 2 diabetes)
countrystring–Country or city with a site (Germany, Boston)
interventionstring–Drug, device or procedure (semaglutide)
limitstring–Results, 1-20 (default 10)
nctstring–One study by id, with eligibility criteria (NCT06283927)
phasestring–Trial phase
qstring–Any words
sponsorstring–Lead sponsor or collaborator (Pfizer)
statusstring–open (default), any, or a comma list: recruiting, not-yet-recruiting, active, enrolling, completed, terminated, withdrawn, suspended

No output schema declared.

No examples provided.

companies_hiring_scan ~244

Which of these companies are hiring, and for what? Give up to 10 company names, websites or job-board URLs, with optional title, location and remote filters. Each company gets its board, open and matching jobs, remote share, top teams, the newest matching jobs, and postings added and removed in the last 7 and 30 days with a growing, steady or shrinking signal, from our crawl history of 18,000+ boards. Ranked by matching jobs, with a one-line summary. Costs $0.02 USDC on Base via x402.

NameTypeReqDescription
companiesstringyesUp to 10 company names (stripe), websites (openai.com) or job-board URLs, comma-separated (a JSON array also works)
jobsPerCompanystring–Newest matching jobs listed per company, 0 to 10 (default 3)
locationstring–Keep jobs whose location or country contains this text (london, remote)
remotestring–true keeps only jobs marked remote
titlestring–Keep jobs whose title contains this text; comma-separate alternatives (engineer,developer)

No output schema declared.

No examples provided.

company_enrich ~115

Company enrichment from a domain: name, description, logo, founded, headquarters, country, industry, employee count, ticker, founders, CEO and parent (Wikidata), social profiles and contact links (homepage), tech stack, mail provider, domain age, careers page and open job count from ~20,000 indexed job boards. Repeat lookups list what changed since the previous check. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
domainstringyesCompany website domain or URL (stripe.com)

No output schema declared.

No examples provided.

company_hiring_movers ~276

Which companies are hiring fastest, or cutting? Ranks companies by job postings added and removed in the last 7, 14 or 30 days, from our recorded history of about 20,000 public company job boards (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, Workday) crawled twice a day. Filter by job function (sales, engineering, data...) to find companies ramping a team. Returns up to 50 companies with open roles, added, removed, net change, growth rate and layoff or hiring-freeze signals. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
daysstring–Window in days (default 7)
directionstring–growing ranks by most postings added net; shrinking by most removed net (default growing)
functionstring–Rank by one job function's net change, read from job titles (e.g. sales)
limitstring–Results, 1-50 (default 25)
minOpenstring–Smallest company to include: open postings at the window's start, 5-5000 (default 10)
staffingstring–Staffing agencies' boards: exclude (default), include, or only

No output schema declared.

No examples provided.

company_hiring_trend ~152

Is a company growing or cutting? Hiring trend from our recorded history of every posting added and removed on its public job board (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, Workday), crawled twice a day: open roles now, added and removed per week, net change and growth rate over 7 and 30 days, teams and locations growing or shrinking, new roles, remote share, and a one-line summary. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
companystringyesCompany name, website or careers-page URL (stripe, openai.com, https://jobs.lever.co/palantir)

No output schema declared.

No examples provided.

company_jobs ~234

Jobs open at a company now, from its public board on Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, BambooHR, Personio, Teamtailor, Rippling, Gem, Breezy or Pinpoint. Give a company name, website or board URL; the board is found from the name, our daily crawl of 18,000+ boards, or links on the company's own site. Filter by title, location or remote. Returns the newest 50 matching jobs (title, location, remote flag, salary when shown, apply link). Costs $0.005 USDC on Base via x402.

NameTypeReqDescription
companystringyesCompany name (stripe), website (stripe.com) or job-board URL (https://jobs.lever.co/palantir)
locationstring–Keep jobs whose location, country or workplace type contains this text (london, remote)
remotestring–true keeps only jobs marked remote
titlestring–Keep jobs whose title contains this text; comma-separate alternatives (engineer,developer)

No output schema declared.

No examples provided.

company_profile ~138

Is a company hiring? A company's hiring profile from its public job board (Greenhouse, Lever, Ashby, Workable, SmartRecruiters, Recruitee, Workday), crawled twice a day: careers page, open roles, top departments, locations and countries, remote share, pay median, newest jobs, and jobs opened and closed in the last 7 and 30 days from our crawl history. Costs $0.01 USDC on Base via x402.

NameTypeReqDescription
companystringyesCompany name, website or careers-page URL (openai, stripe.com, https://jobs.lever.co/palantir)

No output schema declared.

No examples provided.

Install

How do I install the onchaincheck MCP server?

onchaincheck is a hosted endpoint at https://onchaincheck.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 · onchaincheck.dev

# add to Claude Code
claude mcp add --transport http lx1112-onchaincheck 'https://onchaincheck.dev/mcp'
Common questions

What is the onchaincheck MCP server?

onchaincheck is an MCP server listed in the public MCP registry as io.github.lx1112/onchaincheck. 100+ pay-per-call tools: token risk, wallet sanctions screening, onchain data, web, company, AI. This page covers its hosted endpoint (https://onchaincheck.dev/mcp).

Is the onchaincheck MCP server safe to use?

onchaincheck scores 64 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 onchaincheck MCP server expose?

onchaincheck exposes 153 tools: canada_sales_tax, canada_business_days, canada_statutory_holidays, fx_ecb_rates, fx_ecb_convert, and 148 more. Their descriptions and schemas cost roughly 23,428 tokens of context every time the server is loaded.

Does the onchaincheck MCP server require authentication?

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

Is the onchaincheck MCP server still maintained?

onchaincheck 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 onchaincheck MCP server?

VerifyMCP ran 11 checks on onchaincheck, covering TLS certificate, HSTS header, DNSSEC, Transport and 7 more. 2 items could not be completed, a gap on our side rather than a finding about onchaincheck: Authorization and HTTPS. 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.