ActionGate

Official6 tools

by api

Pre-execution safety layer for autonomous agent wallets via MCP and x402.

Safety layer for autonomous agent wallets that validates transactions before execution.

Captured live from the server via tools/list.

request_api_key

Provision a prepaid ActionGate API key with $1.00 of starter credits for this operator email.

Parameters (1)

emailstringrequired
Operator email address that should own the API key.

balance

Return the current prepaid credit balance and usage count for an ActionGate API key.

Parameters (1)

api_keystringrequired
ActionGate API key.

top_up

Generate a Stripe Checkout link so the human operator can add prepaid credits to an existing ActionGate API key.

Parameters (2)

api_keystringrequired
Existing ActionGate API key to top up.
tierstring
Credit pack tier. Defaults to starter.

risk_score

Score the risk of a proposed agent action before execution. Paid via x402 or API key credits. Free tier: 20 risk score calls/day per client.

Parameters (4)

request_idstring
Optional caller-supplied request identifier for tracing and receipts.
actorobjectrequired
Actor metadata for the agent proposing the action.
actionobjectrequired
Action payload to evaluate. Additional action-specific fields are accepted as passthrough.
contextobject
Optional execution context such as chain state, balances, or treasury metadata.

simulate

Estimate cost, failure risk, and notable side effects for a proposed action. Paid via x402 or API key credits. Free tier: 20 simulate calls/day per client.

Parameters (4)

request_idstring
Optional caller-supplied request identifier for tracing and receipts.
actorobjectrequired
Actor metadata for the agent proposing the action.
actionobjectrequired
Action payload to evaluate. Additional action-specific fields are accepted as passthrough.
contextobject
Optional execution context such as chain state, balances, or treasury metadata.

policy_gate

Apply treasury policy to a proposed action and return allow, deny, or allow-with-limits. Paid via x402 or API key credits. Free tier: 10 policy gate calls/day per client.

Parameters (5)

request_idstring
Optional caller-supplied request identifier for tracing and receipts.
actorobjectrequired
Actor metadata for the agent proposing the action.
actionobjectrequired
Action payload to evaluate. Additional action-specific fields are accepted as passthrough.
policyobjectrequired
Policy pack input, including policy_id and any policy-specific override values.
contextobject
Optional execution context such as chain state, balances, or treasury metadata.

Install

Tools (6)

request_api_keybalancetop_uprisk_scoresimulatepolicy_gate

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.actiongate.xyz/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "actiongate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.actiongate.xyz/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.