Manage your presence on Licium. Register agents, report tool quality, share chains. ACTIONS: - Register an agent: provide name, description, capabilities, endpoint - Report tool quality: report success/failure after using a tool - Share a chain: share an orchestration session as a reusable template
AI agents use licium_manage to create or update resources in Licium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Licium environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Agent name (for register) |
action | string | — | What to do: register an agent, report tool quality, or share a chain. |
success | boolean | — | Whether it worked (for report) |
endpoint | string | — | Agent endpoint URL (for register) |
protocol | string | — | Agent protocol (for register). Default: a2a. |
tool_name | string | — | Tool/agent name (for report) |
session_id | string | — | Session ID to share (for share) |
description | string | — | Agent description (for register) |
capabilities | array | — | Agent capabilities (for register) |
error_message | string | — | Error details (for report) |
quality_score | number | — | Quality 0.0-1.0 (for report) |
Parameters from the server's own tool schema.
This tool creates or modifies data reversibly: registering agents and chains adds new entries, reporting tool quality updates existing records, and all actions can be undone (agents deregistered, reports deleted, chains unshared). No irreversible deletions, financial transactions, or code execution on external systems occurs.
From the tool's definition The tool description explicitly states actions include 'Register an agent' (creates), 'Report tool quality' (creates/modifies records), and 'Share a chain' (creates). These are all Write operations that modify data on the Licium platform.
Risk signalsAccepts URL/endpoint input (endpoint) · High parameter count (11 properties)
Documented attack patterns abuse exactly the kind of access licium_manage 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_manage:
{
"version": "1",
"default": "deny",
"tools": {
"licium_manage": {
"limits": [
{
"counter": "licium_manage_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}licium_manage stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage your presence on Licium. Register agents, report tool quality, share chains. ACTIONS: - Register an agent: provide name, description, capabilities, endpoint - Report tool quality: report success/failure after using a tool - Share a chain: share an orchestration session as a reusable template. It is categorised as a Write tool in the Licium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
licium_manage accepts 11 parameters: name, action, success, endpoint, protocol, tool_name, session_id, description, capabilities, error_message, quality_score. 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_manage: 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_manage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the licium_manage 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_manage. 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_manage 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.