Search ACROSS multiple MCP servers in a single call. Returns relevant tools per server, sorted by relevance. Replaces N sequential discover+capabilities calls. Requires AGENTFORGE_API_KEY (set in env or call register_agent first). Use this when an agent needs to fan out a query like
AI agents call broadcast_search to retrieve information from Agentforge Trust without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
broadcast_search queries and retrieves information about available tools across MCP servers. It is a read-only discovery operation that retrieves data without creating, modifying, deleting, or executing code.
From the tool's definition Tool description states it 'Search[es] ACROSS multiple MCP servers in a single call' and 'Returns relevant tools per server'. The verb 'search' and 'returns' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Search ACROSS multiple MCP servers in a single call. Returns relevant tools per server, sorted by relevance. Replaces N sequential discover+capabilities calls. Requires AGENTFORGE_API_KEY (set in env or call register_agent first). Use this when an agent needs to fan out a query like. It is categorised as a Read tool in the Agentforge Trust MCP Server, which means it retrieves data without modifying state.
Register the Agentforge Trust MCP server in PolicyLayer and add a rule for broadcast_search: 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 Agentforge Trust. Nothing to install.
broadcast_search 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 broadcast_search 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 broadcast_search. 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.
broadcast_search is provided by the Agentforge Trust MCP server (kovy/agentforge-trust-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →