invoke_agent

SERVERA2wave SOURCELilithGames/a2wave

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/a2wave/invoke-agent.md

WHAT IT DOES

What invoke_agent does on A2wave

AI agents invoke invoke_agent to trigger actions in A2wave. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

RISK

Why invoke_agent is rated High

Invokes external agents to execute arbitrary tasks with inherited timeouts and reconnection capabilities, creating uncontrolled side effects.

From the tool's definition Send a message to an Agent over the A2A protocol and get its response. Long-running Tasks.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs invoke_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and A2wave, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For invoke_agent, this is the rule to start with:

invoke_agent Rate-limited

invoke_agent stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "invoke_agent": {
      "limits": [
        {
          "counter": "invoke_agent_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect A2wave, apply this rule, and every invoke_agent call is checked against it from then on.

FAQ

Questions about invoke_agent

What does the invoke_agent tool do? +

Send a message to an Agent over the A2A protocol and get its response. Long-running Tasks inherit the calling Agent run timeout and can reconnect by Task ID. Important: relay the complete returned result to the user — do not just reply. It is categorised as a Execute tool in the A2wave MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on invoke_agent? +

Register the A2wave MCP server in PolicyLayer and add a rule for invoke_agent: 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 A2wave. Nothing to install.

What risk level is invoke_agent? +

invoke_agent is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit invoke_agent? +

Yes. Add a rate_limit block to the invoke_agent 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.

How do I block invoke_agent completely? +

Set action: deny in the PolicyLayer policy for invoke_agent. 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.

What MCP server provides invoke_agent? +

invoke_agent is provided by the A2wave MCP server (LilithGames/a2wave). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on A2wave, and thousands of servers like it.

This server

All 22 A2wave tools → High-risk tools on this server →

Across the catalogue

qt_invoke_slot on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →