AI agents invoke send_message to trigger actions in MCP-A2A-Gateway. 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.
The tool name 'send_message' combined with the server's purpose of agent-to-agent communication strongly suggests this tool sends messages to external A2A agents, triggering operations or task execution on those agents. This constitutes an external operation trigger, placing it in the Execute category. Severity is high because sending messages to agents could cause cascading actions across agent systems.
From the tool's definition Tool name 'send_message' on a server that 'enables MCP-compatible AI assistants to discover, register, communicate with, and manage tasks on A2A agents through a unified interface'
Documented attack patterns abuse exactly the kind of access send_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-A2A-Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for send_message:
{
"version": "1",
"default": "deny",
"tools": {
"send_message": {
"limits": [
{
"counter": "send_message_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send_message 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.
Free to start. No card required.
send_message. It is categorised as a Execute tool in the MCP-A2A-Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP-A2A-Gateway MCP server in PolicyLayer and add a rule for send_message: 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 MCP-A2A-Gateway. Nothing to install.
send_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_message 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 send_message. 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.
send_message is provided by the MCP-A2A-Gateway MCP server (yw0nam/mcp_a2a_gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-A2A-Gateway, 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.
6 MCP-A2A-Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.