base-token-audit
Provides ERC-20 token risk analysis and swap route data for tokens on Ethereum (and Base), including contract owner-power checks, honeypot risk signals, quotes, approval targets, and unsigned swap transactions.
Enables purchasing prepaid API call packs by card through Stripe when an agent's free calls are exhausted.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
mcp-base-token-audit
ERC-20 honeypot check and swap route data — a single-purpose MCP server for AI agents. No install, no account: it runs as a remote server; this repo also has a zero-dependency stdio bridge.
https://angel.oroboros-design.com/mcp/base-token-auditUse it
Claude Code
claude mcp add --transport http base-token-audit https://angel.oroboros-design.com/mcp/base-token-auditClaude Desktop, Cursor, Windsurf, VS Code (remote server)
{ "mcpServers": { "base-token-audit": { "url": "https://angel.oroboros-design.com/mcp/base-token-audit" } } }Any stdio client (Node 18+)
{ "mcpServers": { "base-token-audit": { "command": "npx", "args": ["-y", "github:daoudandiaye98-alt/mcp-base-token-audit"] } } }Then ask your agent, for example: Before swapping 10 USDC into 0x… on Base, run token_risk; only if the risk is low, ask get_swap_route for the transaction.
Related MCP server: crypto-inspector-mcp
Tools
Tool | Price | What it does |
| 3 free calls per agent, then 0.99 USDC | Reads the contract: upgradeable proxy (EIP-1967, beacon, clone), owner powers in the bytecode (mint, pause, blacklist, fee or max-tx setters, trading switch, burn from any address), owner renounced or active and owner share of supply. Risk |
| free | Best route on Base or Ethereum (KyberSwap, 0x as fallback): quote, minimum out, approval target and, with |
| — | Prepaid calls by card (Stripe) when the free calls are used up. |
Paying
The first 3 paid calls per agent are free (identify your agent with the header X-API-Key, or set ANGEL_API_KEY for the stdio bridge). After that each call is paid per request in USDC on Base via x402 (params._meta["x402/payment"]), with a prepaid pack (bundle_token) or by card (buy_pack_with_card). The 402 answer names the exact amount and the pay-to address before anything is signed.
Angel is a technical data and risk-analysis service only: no custody, no execution or transmission of orders, no investment advice. The disclosed 0.5 % integrator fee is a technical API provisioning fee for computing the route data; the aggregator deducts it inside a swap you send yourself. Signals from on-chain code — sell restrictions that only trigger during a trade are not simulated.
More
Same checks as a library:
npm i angel-agent-guard·pip install angel-agent-guard(angel-agent-guard)All of Angel's tools in one server:
https://angel.oroboros-design.com/agenten/signal/mcp· A2A agent card:https://angel.oroboros-design.com/.well-known/agent.jsonMCP Registry:
com.oroboros-design.angel/base-token-audit
Operated by Oroboros Design (Köln, Germany). MIT licence for the code in this repo.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
Trading tools for AI agents: token risk checks, swap quotes, unsigned swaps, holdings on 5 chains.
Pre-trade token safety checks for AI agents on Solana and Base. x402 USDC per call, no key.
Related MCP Servers
- 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.139 npmMIT
- AlicenseBqualityDmaintenanceEnables AI agents to perform token security audits, honeypot detection, liquidity analysis, and risk scoring to avoid crypto scams.1ISC

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- AlicenseAqualityBmaintenanceEnables AI coding assistants and trading bots to verify smart contracts, test honeypot traps, assess DEX liquidity, and check wallet counterparty risk before deploying or trading capital on Base. It exposes preflight clearance, token audits, KYA reputation, and web-scraping tools with free and paid x402 tiers.7142 npmMIT