Automaton Token Safety MCP Server

What this does

Automaton Token Safety exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation.

Requirements

This server needs the following environment variables to be set before it can run:

VALUE_API_BASE
AUTOMATON_ORIGIN_BASE
AUTOMATON_MCP_PAYER_KEY
ALLOW_OUTBOUND_SPEND
AUTOMATON_MCP_MAX_AMOUNT_UNITS
AUTOMATON_MCP_TOTAL_CAP_UNITS
MCP_HTTP_PORT

Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).

How do I install Automaton Token Safety?

Run the Claude Code command in the install section to add Automaton Token Safety to Claude Code, or copy the ready-made config for your client from the install section on this page. Restart your client afterwards and the tools appear in your next conversation.

Which clients work with Automaton Token Safety?

This page carries setup and config for Claude Code, Claude Desktop, Cursor and VS Code. Any other MCP client that accepts a standard server config can connect to Automaton Token Safety as well.

Does Automaton Token Safety need an API key?

Yes. Before it can run, set these environment variables: VALUE_API_BASE, AUTOMATON_ORIGIN_BASE, AUTOMATON_MCP_PAYER_KEY, ALLOW_OUTBOUND_SPEND, AUTOMATON_MCP_MAX_AMOUNT_UNITS, AUTOMATON_MCP_TOTAL_CAP_UNITS, MCP_HTTP_PORT. They go in the env block of your MCP config.