Medium Risk

omniwire_agent_registry

Register/discover agents on the mesh. Agents announce their capabilities and other agents can discover them. Enables dynamic A2A routing and capability-based task delegation.

How to control omniwire_agent_registry ↓

What omniwire_agent_registry does on OmniWire

AI agents use omniwire_agent_registry 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.

Medium Risk

Why omniwire_agent_registry needs a policy

The tool performs both registration (Write — creating/modifying registry entries for agents) and discovery (Read — querying existing agents). Since registration is a write operation that modifies the mesh's agent registry, and per the rules the most severe applicable category wins, this is classified as Write.

From the tool's definition Register/discover agents on the mesh. Agents announce their capabilities and other agents can discover them.

Documented attack patterns abuse exactly the kind of access omniwire_agent_registry gives an agent:

How to control omniwire_agent_registry

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_agent_registry:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "omniwire_agent_registry": {
      "limits": [
        {
          "counter": "omniwire_agent_registry_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

omniwire_agent_registry 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.

  1. Create a free account and register OmniWire — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about omniwire_agent_registry

What does the omniwire_agent_registry tool do? +

Register/discover agents on the mesh. Agents announce their capabilities and other agents can discover them. Enables dynamic A2A routing and capability-based task delegation. 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.

How do I enforce a policy on omniwire_agent_registry? +

Register the OmniWire MCP server in PolicyLayer and add a rule for omniwire_agent_registry: 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.

What risk level is omniwire_agent_registry? +

omniwire_agent_registry is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit omniwire_agent_registry? +

Yes. Add a rate_limit block to the omniwire_agent_registry 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 omniwire_agent_registry completely? +

Set action: deny in the PolicyLayer policy for omniwire_agent_registry. 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 omniwire_agent_registry? +

omniwire_agent_registry 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.

Enforce policy on every OmniWire tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.