Medium Risk

manage_credentials

Manage credentials stored in Kernel for managed auth.

How to control manage_credentials ↓

What manage_credentials does on Kernel MCP Server

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

Medium Risk

Why manage_credentials needs a policy

This tool allows modification of stored credentials, which constitutes a Write operation. While credential manipulation could theoretically enable authentication bypass (Execute-like severity), the tool itself performs reversible data operations (create/update/delete credentials) rather than executing code or commands.

From the tool's definition Tool name 'manage_credentials' and description 'Manage credentials stored in Kernel for managed auth' indicate the ability to create, modify, or update credentials. The verb 'manage' encompasses write operations on sensitive authentication material.

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

How to control manage_credentials

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

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

manage_credentials 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 Kernel MCP Server — 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_credentials

What does the manage_credentials tool do? +

Manage credentials stored in Kernel for managed auth. It is categorised as a Write tool in the Kernel MCP Server 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_credentials? +

Register the Kernel MCP Server MCP server in PolicyLayer and add a rule for manage_credentials: 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 Kernel MCP Server. Nothing to install.

What risk level is manage_credentials? +

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

Can I rate-limit manage_credentials? +

Yes. Add a rate_limit block to the manage_credentials 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_credentials completely? +

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

manage_credentials is provided by the Kernel MCP Server MCP server (kernel/kernel-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 Kernel MCP Server tool call.

Start from Kernel MCP Server, 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.

16 Kernel MCP Server 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.