Automaton Token Safety MCP Server
io.github.baianomarceloeduardo-jpg/automaton-token-safety-mcp
What is the Automaton Token Safety MCP server?
Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.
How to install Automaton Token Safety
Copy-paste configuration for popular MCP clients.
VALUE_API_BASErequiredBase URL of the Automaton Token Safety API the tools call.
AUTOMATON_ORIGIN_BASEOrigin URL for routes the edge defers with a use_origin answer (for example the free conformance checker). Optional; without it such a tool reports which variable to set.
AUTOMATON_MCP_PAYER_KEYsecretPrivate key of the wallet that pays for calls. The server only SIGNS an EIP-3009 authorisation; it never sends a transaction. Also required: ALLOW_OUTBOUND_SPEND=1, and this key is not loaded into the process without it. Never set this to the payee/treasury wallet: that is rejected.
ALLOW_OUTBOUND_SPENDSet to 1 to permit this server to sign paid calls. Any other value (including absent) leaves every paid tool answering with the price only.
AUTOMATON_MCP_MAX_AMOUNT_UNITSPer-call ceiling in USDC base units (6 decimals, so 10000 = 0.01 USDC). A requirement above it is refused before signing.
AUTOMATON_MCP_TOTAL_CAP_UNITSCeiling for the whole process lifetime, in USDC base units. Stops a runaway loop, not just a single expensive call.
MCP_HTTP_PORTWhen set, serve Streamable HTTP on this port instead of stdio. Binds to 127.0.0.1 by default.
Related MCP servers
Let AI agents query and operate business systems with authorization, approval and audit trails.

io.github.baixianger/camoufox-mcp
Anti-detection browser automation with Camoufox - stealth Firefox for web scraping

io.github.baixianger/langchain-mcp
LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like)
NBA/WNBA betting analytics: live odds, sharp fair prices, injuries, and prop verification.
Connect OpenEvidence medical research to AI agents via authenticated browser session—no API key required.


