remove_account

// WHEN AI AGENTS USE THIS TOOL

AI agents may call remove_account to permanently remove or destroy resources in Mailbox. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.

// WHY ENFORCE A POLICY ON REMOVE_ACCOUNT

Without a policy, an AI agent could call remove_account in a loop, permanently destroying resources in Mailbox. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.

// RECOMMENDED POLICY

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

mailbox.yaml

tools:
  remove_account:
    rules:
      - action: deny
        reason: "Blocked by default — enable with approval"

See the full Mailbox policy for all 49 tools.

// DETAILS

Tool Name remove_account

Category Destructive

MCP Server Mailbox MCP Server

Risk Level Critical

// MORE MAILBOX TOOLS

Destructive delete_draft Destructive delete_filter Destructive delete_label Destructive delete_template Execute reauth Write archive_email Write authenticate Write batch_modify_emails

View all 49 tools →

// WHAT CAN GO WRONG

Agents calling destructive-class tools like remove_account have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER DESTRUCTIVE TOOLS ACROSS MCP SERVERS

Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.

AbraFlexi contact_delete AbraFlexi evidence_delete AbraFlexi invoice_issued_delete AbraFlexi product_delete ACR — Agent Composition Records acknowledge_signal AdButler campaign_bulk_delete_catalog_ad_items

// IN CONTEXT OF CRITICAL RISK

remove_account is one of the critical-risk operations in Mailbox. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.

// RELATED READING

// FAQ

What does the remove_account tool do? +

Remove a configured email account and its stored credentials. It is categorised as a Destructive tool in the Mailbox 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 remove_account? +

Add a rule in your Intercept YAML policy under the tools section for remove_account. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Mailbox MCP server.

What risk level is remove_account? +

remove_account 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 remove_account? +

Yes. Add a rate_limit block to the remove_account rule in your Intercept 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 remove_account completely? +

Set action: deny in the Intercept policy for remove_account. 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 remove_account? +

remove_account is provided by the Mailbox MCP server (mailbox-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.