BlockchainAnalysis
by blockchainanalysis.io · remote · no sign-in to list tools · v1.2.0 · published by io.blockchainanalysis
Compliance MCP for AI agents: sanctions & KYT screening on 50+ chains, stablecoin-freeze, oracle.
13 tools: 1 do something that can't be undone, 9 change things and 3 only read.
Scanned Oct 21, 2026
- Deletes or cancels0Claude Code: deny
- Can't be undone1Claude Code: ask: see these tools
- Changes things9Claude Code: ask: see these tools
- Only reads3Claude Code: allow: see these tools
2 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http blockchainanalysis https://blockchainanalysis.io/api/mcpFindings
Matches of fixed checks, with the text they matched.
- Warnkyt_tx
The server marks "kyt_tx" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
- Warnlabel
The server marks "label" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "label" says "label": a word for a change.
Tools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
13 tools
Can't be undone 1Claude Code: ask
kyt_txTransaction KYT: screens BOTH counterparties of a transfer (from → to) against sanctions + entity + VASP + cluster, returning a combined risk level, a block/review/allow recommenda…1 finding
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "kyt_tx" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The input addresses people (input.to): what it sends cannot be taken back.
Description, as the server wrote it Transaction KYT: screens BOTH counterparties of a transfer (from → to) against sanctions + entity + VASP + cluster, returning a combined risk level, a block/review/allow recommendation, and directional FROM:/TO: flags. Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Changes things 9Claude Code: ask
check_stablecoin_freezeCheck whether Tether (USDT) or Circle (USDC) have blacklisted a wallet address on-chain.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Check whether Tether (USDT) or Circle (USDC) have blacklisted a wallet address on-chain. Reads the issuer's blacklist function directly across 15 chains (ETH, BSC, POLYGON, ARBITRUM, OPTIMISM, BASE, AVALANCHE, PLASMA, HYPEREVM, STABLE, INK, BERACHAIN, ROBINHOOD, TRON, SOL). A frozen address can no longer send or receive that stablecoin. Also reports whether the address was PREVIOUSLY frozen and later unfrozen (a prior-freeze signal from the freeze ledger). The result reports the observed on-chain fact (frozen / not frozen at check time), never the cause of a freeze. Free.
Annotations the server declares
- title: Check stablecoin freeze
- readOnlyHint: true
- openWorldHint: true
check_token_securitySimulate a buy-and-sell of an ERC-20 token on its main DEXes to surface honeypots (tokens you can buy but not sell), extreme transfer taxes, name/symbol impersonation, and active m…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Simulate a buy-and-sell of an ERC-20 token on its main DEXes to surface honeypots (tokens you can buy but not sell), extreme transfer taxes, name/symbol impersonation, and active mint authority — cross-referenced against BA's 1B+ entity labels. Reports observed facts (e.g. 'sell simulation reverted'), not verdicts. Live on Base, BNB Chain, Ethereum, Optimism, Polygon, Arbitrum. No transaction is sent. Free.
Annotations the server declares
- title: Check token security
- readOnlyHint: true
- openWorldHint: true
kyt_riskAssess a wallet's KYT (Know-Your-Transaction) risk: sanctions + entity classification + VASP/jurisdiction score + cluster context → one risk verdict (critical / high / medium / low…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Assess a wallet's KYT (Know-Your-Transaction) risk: sanctions + entity classification + VASP/jurisdiction score + cluster context → one risk verdict (critical / high / medium / low / unknown) with flags. Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
labelLook up BlockchainAnalysis's entity labels for a single address: every label on record (sanctions from OFAC / EU / UN / UK HMT / Swiss SECO, issuer-freeze state, scam, phishing, ex…1 finding
Why it is in this group
- The name "label" says "label": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "label" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "label" says "label": a word for a change.
Description, as the server wrote it Look up BlockchainAnalysis's entity labels for a single address: every label on record (sanctions from OFAC / EU / UN / UK HMT / Swiss SECO, issuer-freeze state, scam, phishing, exploit, mixer, exchange, and more), each with its category, threat level (SAFE to CRITICAL), and full provenance (source, source URL, confidence, and the date it was last verified). This is the raw label read behind BA Intel, the only way to buy it per call with no account and no API key. An address we hold no label for returns an explicit not-found with the reason, never an empty result, and an absent label is not a statement that the address is safe. Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
oracle_verdictConsumer-protection verdict for a wallet or contract: a normalized verdict (safe / warning / danger, or unknown) with a 0-100 score, confidence tier, and plain-language reasons.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Consumer-protection verdict for a wallet or contract: a normalized verdict (safe / warning / danger, or unknown) with a 0-100 score, confidence tier, and plain-language reasons. Answers 'is it safe to interact with this address?' Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
rwaIdentify a tokenized real-world asset from its token address: what it represents, who issues it, its asset class, ISIN and issuer jurisdiction, whether transfers are permissioned, …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Identify a tokenized real-world asset from its token address: what it represents, who issues it, its asset class, ISIN and issuer jurisdiction, whether transfers are permissioned, and every chain the issuer publishes it on. Each answer carries its provenance: the issuer source, how the address was established (issuer-registry / issuer-page-only / third-party), a confidence, and the date the address was last round-tripped on-chain. An address we do not recognise returns an explicit not-found with the reason, never an empty result. Does NOT cover the issuer's control over a balance (pause, blocklist, seizure). Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
screen_addressScreen a wallet against BlockchainAnalysis's 1B+ entity-label dataset: sanctions (OFAC / EU / UN / UK HMT / Swiss SECO), scam, phishing, exploit, mixer, exchange, and more — each l…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Screen a wallet against BlockchainAnalysis's 1B+ entity-label dataset: sanctions (OFAC / EU / UN / UK HMT / Swiss SECO), scam, phishing, exploit, mixer, exchange, and more — each label carries a threat level (SAFE→CRITICAL), source, and confidence. Works across major EVM chains plus TRON, SOL, and BTC. Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
screen_agent_walletBoolean compliance verdict for an agent wallet or counterparty: clear / flagged / unknown, plus the top risk category, screened against BA's 1B+ entity labels (sanctions, scam, phi…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Boolean compliance verdict for an agent wallet or counterparty: clear / flagged / unknown, plus the top risk category, screened against BA's 1B+ entity labels (sanctions, scam, phishing, exploit, mixer) and live stablecoin freeze state. Deliberately a verdict only — the label detail, freeze history, and scores are in the paid screen_address / kyt_risk tools, and a signed, on-chain-anchored proof is in the paid screen_agent_wallet_attested tool. Free.
Annotations the server declares
- title: Screen agent wallet (verdict)
- readOnlyHint: true
- openWorldHint: true
screen_agent_wallet_attestedScreen an agent wallet and return a SIGNED, on-chain-anchored compliance attestation: the verdict (clear / flagged / unknown) plus an EIP-712 (secp256k1) signature over the result …No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Screen an agent wallet and return a SIGNED, on-chain-anchored compliance attestation: the verdict (clear / flagged / unknown) plus an EIP-712 (secp256k1) signature over the result and a BA Stamp anchor, so a third party or a smart contract can verify it offline via ecrecover without trusting us live. The free screen_agent_wallet tool returns the verdict only. Paid per call via x402 (USDC on Base).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 3Claude Code: allow
check_token_approvalsList a wallet's active ERC-20 token approvals on Ethereum and who can move its funds — risk-scored against BA's 1B+ entity labels (scam / phishing / exploit / sanctioned spenders),…No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List a wallet's active ERC-20 token approvals on Ethereum and who can move its funds — risk-scored against BA's 1B+ entity labels (scam / phishing / exploit / sanctioned spenders), flagging unlimited allowances and stale grants. The wallet's attack surface at a glance. Read-only. Ethereum only. Free.
Annotations the server declares
- title: Check token approvals
- readOnlyHint: true
- openWorldHint: true
get_freeze_eventsQuery the canonical stablecoin freeze ledger — the HISTORY of freeze / unfreeze / destroy events by Tether (USDT), Circle (USDC/EURC), Paxos (USDP) and First Digital (FDUSD), sourc…No findings
Why it is in this group
- The name "get_freeze_events" says "get": a word for reading.
Description, as the server wrote it Query the canonical stablecoin freeze ledger — the HISTORY of freeze / unfreeze / destroy events by Tether (USDT), Circle (USDC/EURC), Paxos (USDP) and First Digital (FDUSD), sourced from the issuers' own on-chain blacklist events across Ethereum, Polygon, Optimism, TRON and more. Filter by frozen address, chain, kind, or time; omit all filters for the most recent events. This is the EVENT HISTORY — to check whether an address is frozen right now, use check_stablecoin_freeze instead. Each row is a verifiable on-chain fact (issuer acted on address at block/time); it never states the cause. Free.
Annotations the server declares
- title: Get stablecoin freeze events (history)
- readOnlyHint: true
- openWorldHint: true
list_supported_chainsList the BlockchainAnalysis MCP tools, the chains each supports, and pricing.No findings
Why it is in this group
- The name "list_supported_chains" says "list": a word for reading.
Description, as the server wrote it List the BlockchainAnalysis MCP tools, the chains each supports, and pricing. Call this first to discover what the server can do (and which calls are free vs paid) before invoking a tool. Free.
Annotations the server declares
- title: List supported chains & tools
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http blockchainanalysis https://blockchainanalysis.io/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__blockchainanalysis__get_freeze_events",
"mcp__blockchainanalysis__check_token_approvals",
"mcp__blockchainanalysis__list_supported_chains"
],
"ask": [
"mcp__blockchainanalysis__check_stablecoin_freeze",
"mcp__blockchainanalysis__check_token_security",
"mcp__blockchainanalysis__screen_agent_wallet",
"mcp__blockchainanalysis__screen_address",
"mcp__blockchainanalysis__kyt_risk",
"mcp__blockchainanalysis__kyt_tx",
"mcp__blockchainanalysis__rwa",
"mcp__blockchainanalysis__label",
"mcp__blockchainanalysis__oracle_verdict",
"mcp__blockchainanalysis__screen_agent_wallet_attested"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as blockchainanalysis. Review it before you use it.