Medium Risk

1ly_create_key

Create a new API key for the authenticated agent store (requires ONELY_API_KEY).

How to control 1ly_create_key ↓

What 1ly_create_key does on 1ly

AI agents use 1ly_create_key to create or update resources in 1ly — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 1ly environment.

ParameterTypeRequiredDescription
name string

Parameters from the server's own tool schema.

Medium Risk

Why 1ly_create_key needs a policy

Creating an API key is a write operation that modifies the store's authentication and access control state. While reversible, it introduces a new credential that could grant access to the store's resources. The 'high' severity reflects that a misused API key could enable unauthorized access to sensitive store operations (payments, token launches, link management) on behalf of the store.

From the tool's definition Tool name '1ly_create_key' explicitly performs 'Create a new API key'. Description states it creates a key for 'the authenticated agent store'. This is a reversible modification (keys can typically be revoked/deleted).

Documented attack patterns abuse exactly the kind of access 1ly_create_key gives an agent:

How to control 1ly_create_key

PolicyLayer is an MCP gateway — it sits between your AI agents and 1ly, and nothing reaches the server without passing your rules. This is the rule we recommend for 1ly_create_key:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "1ly_create_key": {
      "limits": [
        {
          "counter": "1ly_create_key_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

1ly_create_key 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.

  1. Create a free account and register 1ly — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about 1ly_create_key

What does the 1ly_create_key tool do? +

Create a new API key for the authenticated agent store (requires ONELY_API_KEY). It is categorised as a Write tool in the 1ly MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does 1ly_create_key accept? +

1ly_create_key accepts 1 parameter: name. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on 1ly_create_key? +

Register the 1ly MCP server in PolicyLayer and add a rule for 1ly_create_key: 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 1ly. Nothing to install.

What risk level is 1ly_create_key? +

1ly_create_key is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit 1ly_create_key? +

Yes. Add a rate_limit block to the 1ly_create_key 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 1ly_create_key completely? +

Set action: deny in the PolicyLayer policy for 1ly_create_key. 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 1ly_create_key? +

1ly_create_key is provided by the 1ly MCP server (@1ly/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every 1ly tool call.

Start from 1ly, 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.

23 1ly tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.