// SCAN REPORT

Mailosaur MCP

29 tools. 12 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

12 can modify or destroy data

17 read-only

29 tools total

Community server · catalogue entry verified 03/07/2026

How to control Mailosaur MCP ↓

TOOL MAP

What Mailosaur MCP exposes to your agents

Read (17) Write / Execute (8) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mailosaur MCP tools

Destructive · High mailosaur_messages_delete_all This tool performs permanent, irreversible deletion of all messages and attachments in a Mailosaur server. Destructive · High mailosaur_devices_delete Mailosaur virtual security devices are testing resources that, once deleted, cannot be recovered. Destructive · High mailosaur_messages_delete This tool irreversibly removes messages and associated files from the Mailosaur service. Destructive · High mailosaur_servers_delete This tool irreversibly deletes data (server and all associated messages) and cannot be undone.

12 of Mailosaur MCP's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mailosaur MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Mailosaur MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "mailosaur_devices_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "mailosaur_devices_create": {
    "limits": [
      {
        "counter": "mailosaur_devices_create_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "mailosaur_analysis_spam": {
    "limits": [
      {
        "counter": "mailosaur_analysis_spam_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mailosaur MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MAILOSAUR →

Instant setup, no code required.

FULL CATALOGUE

All 29 Mailosaur MCP tools

DESTRUCTIVE 4 tools

Destructive mailosaur_devices_delete Permanently delete a Mailosaur virtual security device. Destructive mailosaur_messages_delete Permanently delete a message and its attachments. Destructive mailosaur_messages_delete_all Permanently delete all messages and attachments on a server. Destructive mailosaur_servers_delete Permanently delete a Mailosaur server and all contained messages.

EXECUTE 2 tools

Execute mailosaur_analysis_deliverability Run deliverability analysis for a message. Execute mailosaur_messages_generate_previews Generate screenshots of an email rendered in selected email clients.

WRITE 6 tools

Write mailosaur_devices_create Create a Mailosaur virtual security device from a base32 shared secret. Write mailosaur_messages_create Create a message and optionally send it to a verified external address. Write mailosaur_messages_reply Reply to an email message. Write mailosaur_servers_create Create a Mailosaur server. Write mailosaur_servers_generate_email_address Generate a random email address for a Mailosaur server. Write mailosaur_servers_update Update a Mailosaur server.

READ 17 tools

Read mailosaur_analysis_spam Run spam analysis for a message. Read mailosaur_devices_list List Mailosaur virtual security devices used for TOTP testing. Read mailosaur_devices_otp Retrieve the current TOTP code for a saved device ID or base32 shared secret. Read mailosaur_files_get_attachment Download a message attachment. Returns base64 content. Read mailosaur_files_get_email Download a message as an EML file. Returns base64 content. Read mailosaur_files_get_preview Download a generated email preview screenshot. Returns base64 content. Read mailosaur_messages_forward Forward an email message to a verified address. Read mailosaur_messages_get Wait for and return the first full message matching criteria. Best for test flows where an email/SMS may arriv Read mailosaur_messages_get_by_id Retrieve the full detail for a single message by ID. Read mailosaur_messages_list List message summaries for a server. Read mailosaur_messages_search Search message summaries by sender, recipient, subject, or body. Read mailosaur_previews_list_email_clients List email clients available for generated email previews. Read mailosaur_servers_get Get a Mailosaur server by ID. Read mailosaur_servers_get_password Get the SMTP/POP3 password for a Mailosaur server. Read mailosaur_servers_list List all Mailosaur servers. Read mailosaur_usage_limits Retrieve account usage limits. Requires an account-level API key. Read mailosaur_usage_transactions Retrieve recent transaction usage. Requires an account-level API key.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mailosaur MCP

Can an AI agent delete data through the Mailosaur MCP server? +

Yes. The Mailosaur MCP server exposes 4 destructive tools including mailosaur_devices_delete, mailosaur_messages_delete, mailosaur_messages_delete_all. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mailosaur MCP? +

The Mailosaur MCP server has 6 write tools including mailosaur_devices_create, mailosaur_messages_create, mailosaur_messages_reply. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mailosaur MCP.

How many tools does the Mailosaur MCP server expose? +

29 tools across 4 categories: Destructive, Execute, Read, Write. 17 are read-only. 12 can modify, create, or delete data.

How do I enforce a policy on Mailosaur MCP? +

Register the Mailosaur MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mailosaur MCP tool call.

Deterministic rules across all 29 Mailosaur MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MAILOSAUR →

Instant setup, no code required.

29 Mailosaur MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.