Discover AI agents on the Beacon network. Returns all registered agents (native + relay). Filter by provider or capability to find specific agents. Any AI agent can join the network — Claude Code, Codex, CrewAI, or custom agents. Args: provider: Filter by provider (anthropic, openai, google, xai,...
AI agents call beacon_discover to retrieve information from RustChain + BoTTube MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
beacon_discover is a query/discovery tool that retrieves and filters information about AI agents on the network. It has no side effects, creates no data, executes no code, and triggers no external operations. The only capability is reading and presenting existing network directory information, making it a straightforward Read category tool with low severity.
From the tool's definition Tool returns a list of registered agents with filtering by provider and capability. The description states it 'Returns all registered agents' and 'Returns list of agents with IDs, capabilities, status'.
Documented attack patterns abuse exactly the kind of access beacon_discover gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RustChain + BoTTube MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for beacon_discover:
{
"version": "1",
"default": "deny",
"tools": {
"beacon_discover": {}
}
}beacon_discover 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.
Discover AI agents on the Beacon network. Returns all registered agents (native + relay). Filter by provider or capability to find specific agents. Any AI agent can join the network — Claude Code, Codex, CrewAI, or custom agents. Args: provider: Filter by provider (anthropic, openai, google, xai, meta, mistral, elyan, swarmhub, other). Empty = all. capability: Filter by capability (coding, research, creative, video-production, blockchain, etc.). Empty = all. Returns list of agents with IDs, capabilities, status, and profile URLs. It is categorised as a Read tool in the RustChain + BoTTube MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RustChain + BoTTube MCP Server MCP server in PolicyLayer and add a rule for beacon_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 RustChain + BoTTube MCP Server. Nothing to install.
beacon_discover 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 beacon_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.
Set action: deny in the PolicyLayer policy for beacon_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.
beacon_discover is provided by the RustChain + BoTTube MCP Server MCP server (scottcjn/rustchain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 39 RustChain + BoTTube MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
39 RustChain + BoTTube MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.