Execute a metered API call through the AgentClear proxy. Costs sub-cent per call, charged to your AgentClear wallet.
AI agents use call_service to commit financial operations through AgentClear — API Marketplace for AI Agents — usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
payload | object | — | JSON request payload |
service_id | string | — | Service ID from discover_services |
Parameters from the server's own tool schema.
Every invocation of this tool draws funds from the user's AgentClear wallet, constituting a real financial transaction. An AI agent could call this tool repeatedly or with expensive service targets, draining the wallet. This meets the Financial category as it directly commits financial obligations per call.
From the tool's definition 'Costs sub-cent per call, charged to your AgentClear wallet' and 'Execute a metered API call through the AgentClear proxy'
Risk signalsAccepts raw HTML/template content (payload)
Documented attack patterns abuse exactly the kind of access call_service gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AgentClear — API Marketplace for AI Agents, and nothing reaches the server without passing your rules. This is the rule we recommend for call_service:
{
"version": "1",
"default": "deny",
"tools": {
"call_service": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
}Any call to call_service is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Execute a metered API call through the AgentClear proxy. Costs sub-cent per call, charged to your AgentClear wallet. It is categorised as a Financial tool in the AgentClear — API Marketplace for AI Agents MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
call_service accepts 2 parameters: payload, service_id. The full parameter table on this page comes from the server's own tool schema.
Register the AgentClear — API Marketplace for AI Agents MCP server in PolicyLayer and add a rule for call_service: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AgentClear — API Marketplace for AI Agents. Nothing to install.
call_service is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the call_service rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for call_service. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
call_service is provided by the AgentClear — API Marketplace for AI Agents MCP server (agentclear-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AgentClear — API Marketplace for AI Agents, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 AgentClear — API Marketplace for AI Agents tools catalogued and risk-classified — across an index of 43,000+ MCP servers.