Automaton Token Safety
Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk.
The current version, v2.0.1, was published to the official MCP registry on 2026-09-27. It is distributed as @celorodrigues/token-safety-mcp on npm and as a hosted remote over streamable-http, filed under Other by this index, and declares 7 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.
Using Automaton Token Safety in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireVerdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-09-28).
Contracts can change after screening, with no version bump. The gate pins Automaton Token Safety’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
VALUE_API_BASEBase 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_KEYPrivate 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.
Hosted MCP for Clip Studio public products — same plan as the website.
Financial data and research MCP for US/CN/JP equities: filings, statements, ownership, signals.
Let AI agents query and operate business systems with authorization, approval and audit trails.