Agent-to-agent messaging via shared message queues on mesh nodes. Agents can send/receive typed messages, enabling multi-agent coordination without direct coupling. Messages are stored on disk and survive process restarts.
AI agents use omniwire_a2a_message to create or update resources in OmniWire — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OmniWire environment.
This tool creates and modifies message queue data on disk without permanently deleting or destroying infrastructure. While it enables inter-agent coordination, the primary action is writing messages to persistent storage. It does not execute arbitrary commands (Execute), delete data (Destructive), transfer funds (Financial), or merely query state (Read).
From the tool's definition Tool description states agents can 'send/receive typed messages' and 'messages are stored on disk', indicating creation and storage of data structures. The messaging infrastructure enables state modification across the mesh infrastructure.
Documented attack patterns abuse exactly the kind of access omniwire_a2a_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OmniWire, and nothing reaches the server without passing your rules. This is the rule we recommend for omniwire_a2a_message:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_a2a_message": {
"limits": [
{
"counter": "omniwire_a2a_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}omniwire_a2a_message stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Agent-to-agent messaging via shared message queues on mesh nodes. Agents can send/receive typed messages, enabling multi-agent coordination without direct coupling. Messages are stored on disk and survive process restarts. It is categorised as a Write tool in the OmniWire MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OmniWire MCP server in PolicyLayer and add a rule for omniwire_a2a_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 OmniWire. Nothing to install.
omniwire_a2a_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the omniwire_a2a_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 omniwire_a2a_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.
omniwire_a2a_message is provided by the OmniWire MCP server (voidchecksum/omniwire). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OmniWire, 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.
88 OmniWire tools catalogued and risk-classified — across an index of 43,000+ MCP servers.