Loading
Local mandate gate and proof trail for AI agents that take consequential actions.
The publisher's own command. Not a PlugMCP endpoint.
npx -y [email protected]
FORGE_API_KEY=<secret> FORGE_BEARER_TOKEN=<secret> FORGE_API_BASE_URL=<value> FORGE_TENANT_ID=<value> FORGE_RECORD_MODE=<value> AGENT_GATE_MANDATE_PATH=<value> AGENT_GATE_KILL_FILE=<value> KALSHI_API_KEY_ID=<secret> KALSHI_PRIVATE_KEY_PATH=<value> KALSHI_ENV=<value> claude mcp add com.forgeorbital-agent-gate -- npx -y [email protected]
Run in a terminal.
{
"mcpServers": {
"com.forgeorbital-agent-gate": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"FORGE_API_KEY": "<secret>",
"FORGE_BEARER_TOKEN": "<secret>",
"FORGE_API_BASE_URL": "<value>",
"FORGE_TENANT_ID": "<value>",
"FORGE_RECORD_MODE": "<value>",
"AGENT_GATE_MANDATE_PATH": "<value>",
"AGENT_GATE_KILL_FILE": "<value>",
"KALSHI_API_KEY_ID": "<secret>",
"KALSHI_PRIVATE_KEY_PATH": "<value>",
"KALSHI_ENV": "<value>"
}
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Local mandate gate and proof trail for AI agents that take consequential actions.
README is not crawled yet. No repository on file.
No tool list yet. Remote servers get one after the first health check.