Query node capabilities for intelligent task routing. Returns what tools, runtimes, and resources each node has. Agents use this to decide WHERE to dispatch tasks.
AI agents call omniwire_capability to retrieve information from OmniWire without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about available resources and capabilities across nodes without modifying state or triggering actions. It is a prerequisite query operation that informs routing decisions but does not itself execute commands, modify data, delete resources, or commit financial obligations.
From the tool's definition Tool explicitly described as 'Query node capabilities' and returns information about 'what tools, runtimes, and resources each node has.' No modification or execution of infrastructure occurs; the tool is used by agents to 'decide WHERE to dispatch tasks' — a…
Documented attack patterns abuse exactly the kind of access omniwire_capability 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_capability:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_capability": {}
}
}omniwire_capability is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Query node capabilities for intelligent task routing. Returns what tools, runtimes, and resources each node has. Agents use this to decide WHERE to dispatch tasks. It is categorised as a Read tool in the OmniWire MCP Server, which means it retrieves data without modifying state.
Register the OmniWire MCP server in PolicyLayer and add a rule for omniwire_capability: 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_capability is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the omniwire_capability 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_capability. 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_capability 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.