// MCP TOOL REFERENCE

licium

ServerLicium
CategoryExecute
Parameters3

WHAT IT DOES

What licium does on Licium

AI agents invoke licium to trigger actions in Licium. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`task`	string	—	What you want done. Be specific.
`max_steps`	integer	—	Max execution steps (default: 7).
`cost_preference`	string	—	Cost vs quality. Default: balanced.

Parameters from the server's own tool schema.

THE RISK

High Risk

Why licium needs a policy

This tool grants an AI agent the ability to invoke thousands of external agents and tools with arbitrary task descriptions. While examples show legitimate queries (price data, drug info, filings), the 'any task' capability and access to 24,866+ tools means an adversary could use it to execute malicious workflows—data exfiltration, unauthorized API calls, social engineering chains across agents, or triggering…

From the tool's definition Tool executes 'any task' through 3,533+ specialist agents and 24,866+ tools with no apparent restrictions.

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

POLICY

How to control licium

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:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "licium": {
      "limits": [
        {
          "counter": "licium_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

licium stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Licium — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Licium tools

Write licium_manage Manage your presence on Licium. Register agents, report tool quality, share chains. ACTIO Read licium_discover Browse and compare Licium's agents and tools. Use this when you want to SEE what's availab

All 3 Licium tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Licium → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about licium

What does the licium tool do? +

Execute any task through Licium's 3,533+ specialist agents and 24,866+ tools. Send a task description. Licium plans, selects the best agent, fetches real data from APIs, and returns results. EXAMPLES: "Bitcoin price right now" → real-time crypto data "Side effects of metformin" → FDA drug database "Tesla 10-K SEC filing" → SEC EDGAR filings "Research AI protocols and create comparison chart" → multi-step orchestration "GitHub API repos endpoint response format" → any public API LIVE DATA: stocks, crypto, FDA drugs, SEC filings, court records, clinical trials, PubMed, weather, any public API. OUTPUT: Pre-formatted markdown. Present as-is. It is categorised as a Execute tool in the Licium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does licium accept? +

licium accepts 3 parameters: task, max_steps, cost_preference. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on licium? +

Register the Licium MCP server in PolicyLayer and add a rule for licium: 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.

What risk level is licium? +

licium is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit licium? +

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

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

licium 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.