Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success r...
AI agents call licium_discover to retrieve information from Licium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
type | string | — | Filter: 'tools' for MCP servers, 'agents' for specialist agents. Default: any. |
limit | integer | — | Max results. Default: 5. |
query | string | — | What you're looking for. Natural language. |
Parameters from the server's own tool schema.
licium_discover is purely informational. It retrieves metadata about available tools and agents, their reputations, success rates, and health status. No side effects, no data modification, no code execution, no financial impact. The tool's purpose is discovery and comparison prior to taking action, making it a straightforward Read category with low severity.
From the tool's definition Tool enables browsing, searching, and comparing agents and tools ('Search tools', 'Search agents', 'Compare', 'Check status', 'Find alternatives'). All operations are read-only queries with no modification, deletion, or execution capabilities.
Risk signalsAccepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access licium_discover gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Licium, and nothing reaches the server without passing your rules. This is the rule we recommend for licium_discover:
{
"version": "1",
"default": "deny",
"tools": {
"licium_discover": {}
}
}licium_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.
Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success rates - Compare: "agents for code review" → ranked by reputation, shows pricing - Check status: "is resend-mcp working?" → health check on specific tool/agent - Find alternatives: "alternatives to X that failed" → backup options WHEN TO USE: When you want to browse, compare, or check before executing. If you just want results, use licium instead. It is categorised as a Read tool in the Licium MCP Server, which means it retrieves data without modifying state.
licium_discover accepts 3 parameters: type, limit, query. The full parameter table on this page comes from the server's own tool schema.
Register the Licium MCP server in PolicyLayer and add a rule for licium_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 Licium. Nothing to install.
licium_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 licium_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 licium_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.
licium_discover is provided by the Licium MCP server (licium/licium). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Licium, 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.
3 Licium tools catalogued and risk-classified — across an index of 43,000+ MCP servers.