Medium Risk

manage_agent_keys

List, create, update, deactivate, or rotate agent keys. Manager only.

How to control manage_agent_keys ↓

What manage_agent_keys does on Writbase

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

Medium Risk

Why manage_agent_keys needs a policy

This tool modifies authentication material (agent keys) through creation, updates, and rotation. While deactivation is reversible (keys can be re-activated or recreated), the core operations are Write-category: creating new credentials and modifying existing ones. It does not permanently destroy data (Destructive) or execute arbitrary code (Execute).

From the tool's definition Tool description explicitly states it can 'create, update, deactivate, or rotate agent keys,' which are reversible modifications to authentication credentials. The 'Manager only' restriction indicates privileged access control.

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

How to control manage_agent_keys

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

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

manage_agent_keys 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 Writbase — 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 manage_agent_keys

What does the manage_agent_keys tool do? +

List, create, update, deactivate, or rotate agent keys. Manager only. It is categorised as a Write tool in the Writbase MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_agent_keys? +

Register the Writbase MCP server in PolicyLayer and add a rule for manage_agent_keys: 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 Writbase. Nothing to install.

What risk level is manage_agent_keys? +

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

Can I rate-limit manage_agent_keys? +

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

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

manage_agent_keys is provided by the Writbase MCP server (https://{PROJECT_REF}.supabase.co/functions/v1/mcp-server/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Writbase tool call.

Start from Writbase, 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.

13 Writbase 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.