Automaton Token Safety
Server Details
Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 20 tools
security_scan and token_scan are explicitly the same route/arguments, and sentiment_analysis overlaps with token_scan/security_scan, so an agent can easily select a redundant path. tx_simulate vs simulate_base_transaction are distinguished mainly by description text, adding naming-induced confusion. Other tools are reasonably distinct, but these overlaps lower clarity.
All tool names use snake_case consistently, with no camelCase or mixed conventions. The verb/noun patterns vary slightly (e.g., attest, read_ledger, merkle_verify) but remain predictable and readable.
20 tools is on the heavy side for the apparent scope; the core token-safety surface is accompanied by several generic crypto utilities (uuid, hash_sha256, merkle_*) and payment/infrastructure checks. It is not extreme, but it exceeds the typical 3-15 well-scoped range.
Coverage is broad: token bytecode scans, approvals, liquidity, sentiment, transaction simulation, new-pool monitoring, attestation lifecycle, and x402 payment conformance are all represented. Minor gaps include no explicit token metadata or batch/multi-token scanning, but core safety and audit workflows are largely supported.
Available Tools
20 toolsapproval_riskAInspect
PAID 0.01 USDC/call, or free trial (3/day/IP). Read-only audit of the ERC-20 approvals an owner granted for a token: spender, allowance, contract vs EOA, verified flag, drainable amount and a drain-risk verdict. On 402, pay the accepts[] terms then retry with the payment tx hash.
Inputs: owner (required), token (required), payment, spenders.
attestAInspect
Create a SIGNED, hash-chained, append-only attestation (verifiable proof-of-existence) for a payload. PAID: 0.05 USDC/call, or free trial (3/day/IP). On 402, pay the accepts[] terms then retry with the payment tx hash.
Inputs: data (required), payment.
attestation_pubkeyAInspect
FREE. Get the ECDSA P-256 public key (PEM) and keyId used to sign ledger entries.
Inputs: no named parameters.
hash_sha256BInspect
PAID 0.001 USDC/call. SHA-256 hex of a string.
Inputs: input (required), payment.
liquidity_riskAInspect
PAID 0.01 USDC/call, or free trial (3/day/IP). One-block liquidity audit of a Base token: Uniswap V3 / Aerodrome pools, the USD needed to move the price 1/2/5/10%, holder concentration, LP burn evidence and explicit coverage gaps. On 402, pay the accepts[] terms then retry with the payment tx hash.
Inputs: token (required), pair, payment.
merkle_proveCInspect
PAID 0.001 USDC/call. Generate a cryptographic Merkle inclusion proof for a list of items and target element.
Inputs: items (required), target, payment.
merkle_verifyCInspect
FREE. Verify a cryptographic Merkle inclusion proof against a root.
Inputs: item (required), root (required), proof (required).
oracle_baseBInspect
PAID 0.001 USDC/call. Get real-time Base L2 gas estimates and asset prices (ETH, USDC, cbBTC, AERO, VIRTUAL) with an ECDSA P-256 digital signature from the sovereign agent.
Inputs: payment.
pricingCInspect
FREE. Full pricing terms, endpoints, and payment mechanics.
Inputs: no named parameters.
read_ledgerCInspect
FREE. Read the attestation ledger (paginated).
Inputs: from, limit.
security_scanAInspect
LEGACY NAME of token_scan — same route, same arguments, kept so clients written against this server keep working. PAID 0.001 USDC/call, or free trial (3/day/IP). Base token safety analysis: honeypot detection, mint traps, selfdestruct/delegatecall, proxy and tax risks from contract bytecode, with a risk score and signed verdict. On 402, pay the accepts[] terms then retry with the payment tx hash.
Inputs: address (required), payment.
sentiment_analysisCInspect
PAID 0.001 USDC/call. Web3 token risk, security checks, and sentiment scoring with signed verdict.
Inputs: asset (required), payment.
sentinel_latestAInspect
PAID 0.001 USDC/call, or free trial (3/day/IP). Newest liquidity pools created on Base (Uniswap v3/v4, Aerodrome) with a bytecode risk score per new token. Filters are optional. On 402, pay the accepts[] terms then retry with the payment tx hash.
Inputs: dex, limit, since, maxRisk, +2 more.
simulate_base_transactionAInspect
FREE, runs locally against Base Mainnet RPC. Dry-run a transaction before sending it: eth_call + eth_estimateGas at the latest block. Predicts whether it will revert and decodes the reason (Error(string), Panic(uint256) codes, custom-error selector, or node rejection such as insufficient funds). Returns { ok, willRevert, revertReason, estimatedGas, returnData }.
Inputs: to (required), data, from, value.
token_scanAInspect
PAID 0.001 USDC/call, or free trial (3/day/IP). Bytecode security scan of a Base token contract: honeypot opcodes, mint/blacklist/pause/tax capabilities, a risk score and a verdict. Read-only — no transaction is sent. On 402, pay the accepts[] terms then retry with the payment tx hash. (Exposed as security_scan on older clients.)
Inputs: address (required), payment.
tx_simulateAInspect
PAID 0.01 USDC/call, or free trial (3/day/IP). Read-only buy/sell simulation of a Base token through the Uniswap V2 WETH pool: returns reverts, the MEASURED transfer tax and a honeypot verdict. No transaction is sent. On 402, pay the accepts[] terms then retry with the payment tx hash. (Not the same tool as simulate_base_transaction, which dry-runs arbitrary calldata for free.)
Inputs: side (required), token (required), amount (required), wallet (required), +1 more.
verify_attestationAInspect
FREE. Verify a ledger entry by index or by data hash: recomputes hash, checks ECDSA signature and chain link.
Inputs: index, dataHash.
x402_conformance_checkAInspect
FREE, runs locally. Lint any x402 paid endpoint for protocol conformance: HTTP 402 challenge, x402Version, accepts[] (exact scheme), Base network and addresses, EIP-712 domain, and rejection of malformed, forged, expired, underpaid and wrong-recipient EIP-3009 payments. Returns verdict, grade and per-check results.
Inputs: url (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy.
On-chain token security, honeypot simulation, KYA wallet trust, and x402 PreFlight audits on Base.
Base crypto safety for agents: honeypot/tax test, address poisoning, rug feed, creator record.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to screen ERC-20 tokens on Base and Ethereum for honeypot and rug-pull risks, including upgradeable proxies, owner powers, and trading restrictions, before swapping or approving. It also provides best swap route quotes with approval targets and unsigned transactions for the agent to sign and send.MIT

AgentRisk MCPofficial
AlicenseAqualityCmaintenanceEnables AI agents on Base to call a check_token_risk tool before trading, providing honeypot detection, LP-lock verification, brand impersonation checks, and live sell simulation across Uniswap V2/V3/V4 and Aerodrome with a clear risk score and should-trade decision.111 npmMIT- AlicenseAqualityDmaintenanceThe safety layer that checks a DeFi transaction or token before your agent (or you) signs — on Base L2.664 npmMIT
- AlicenseAqualityDmaintenancebasescope is a read-only onchain safety layer for AI agents: it answers "is this token/contract/approval safe?" on Base and EVM chains (honeypot/rug checks, risky-approval detection, verified-source lookup, balances, ENS/Basenames, gas, prices), with no private keys and no required API keys.136 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.