delete_credential

THE RISK

Critical Risk

Why delete_credential needs a policy

This tool irreversibly deletes data (stored credentials) and cannot be undone, which is the defining characteristic of the Destructive category. While not financial in nature, the permanent deletion of authentication credentials could have severe cascading impacts on system access and security posture if misused by an AI agent.

From the tool's definition Tool name and description: 'Permanently delete a stored credential' - the word 'Permanently' indicates irreversible deletion with no undo capability.

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

POLICY

How to control delete_credential

PolicyLayer is an MCP gateway — it sits between your AI agents and Chrome MCP Server (Security Hardened), and nothing reaches the server without passing your rules. This is the rule we recommend for delete_credential:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_credential"
  ]
}

delete_credential disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

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

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Chrome MCP Server (Security Hardened) tools

Execute secure_login Perform a secure login using stored credentials. Automatically fills in username/email and Write store_credential Securely store login credentials with post-quantum encryption. Credentials are encrypted a Write update_credential Update an existing credential. Only provided fields will be updated. Read get_credential Get a specific credential by ID. Returns metadata only - use secure_login for authenticati Read get_vault_status Get the status of the credential vault including encryption configuration. Read list_credentials List all stored credentials. Returns metadata only - no passwords or API keys are exposed.

All 7 Chrome MCP Server (Security Hardened) tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Chrome MCP Server (Security Hardened) → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-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.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about delete_credential

What does the delete_credential tool do? +

Permanently delete a stored credential. It is categorised as a Destructive tool in the Chrome MCP Server (Security Hardened) MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on delete_credential? +

Register the Chrome MCP Server (Security Hardened) MCP server in PolicyLayer and add a rule for delete_credential: 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 Chrome MCP Server (Security Hardened). Nothing to install.

What risk level is delete_credential? +

delete_credential is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit delete_credential? +

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

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

delete_credential is provided by the Chrome MCP Server (Security Hardened) MCP server (pantheon-security/chrome-mcp-secure). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Chrome MCP Server (Security Hardened) tool call.

Start from Chrome MCP Server (Security Hardened), add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →