acp_discover

Discover ACP/A2A agents that CoWork can delegate work to. Use this before selecting acp_agent_id for spawn_agent or orchestrate_agents.

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-os/acp-discover.md

WHAT IT DOES

What acp_discover does on CoWork OS

AI agents call acp_discover to retrieve information from CoWork OS without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why acp_discover is rated Low

The tool reads and returns information about available agents. It has no side effects — it is explicitly described as a prerequisite lookup step ('Use this before selecting acp_agent_id') rather than performing any action itself. No data is created, modified, executed, or deleted.

From the tool's definition 'Discover ACP/A2A agents' — this is a discovery/query operation used to list available agents before delegation

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs acp_discover safely

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

acp_discover Allowed

acp_discover is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "acp_discover": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about acp_discover

What does the acp_discover tool do? +

Discover ACP/A2A agents that CoWork can delegate work to. Use this before selecting acp_agent_id for spawn_agent or orchestrate_agents. It is categorised as a Read tool in the CoWork OS MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on acp_discover? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for acp_discover: 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 CoWork OS. Nothing to install.

What risk level is acp_discover? +

acp_discover is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit acp_discover? +

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

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

acp_discover is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on CoWork OS, and thousands of servers like it.

This server

All 342 CoWork OS tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →