// SCAN REPORT

AgenticEmail

9 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 18 Aug 2026

3 can modify or destroy data

6 read-only

9 tools total

Community server · catalogue entry checked 09/07/2026 · full schemas captured for 8 of 9 tools

How to control AgenticEmail ↓

TOOL MAP

What AgenticEmail exposes to your agents

Read (6) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What AgenticEmail costs in tokens

707 tokens of tool definitions, loaded on every request

0.4% of a 200k context window

129 heaviest tool: read_attachment

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

High Risk

The most dangerous AgenticEmail tools

Write · Medium create_inbox This tool creates or modifies data (a new inbox resource) without permanently deleting or overwriting existing data, making it a Write operation. Write · Medium reply_to_message This tool creates new email messages and sends them, which constitutes data modification. Write · Medium send_message Sending an email creates and transmits new data, which is a Write operation.

3 of AgenticEmail's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control AgenticEmail

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

Rate limit write operations

{
  "create_inbox": {
    "limits": [
      {
        "counter": "create_inbox_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_message": {
    "limits": [
      {
        "counter": "get_message_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 AgenticEmail — 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 AGENTICEMAIL →

Instant setup, no code required.

FULL CATALOGUE

All 9 AgenticEmail tools

WRITE 3 tools

Write create_inbox Create a new inbox. Omit username for a random one; omit domain to use the default (or only verified) domain. Write reply_to_message Reply to a message; recipients, subject and threading are set automatically. Write send_message Send a new email from an inbox.

READ 6 tools

Read get_message Get a single message by id, including attachment metadata. Use read_attachment to read attachment contents. Read get_thread Get a thread with all its messages. Read list_inboxes List all inboxes in the account. Read list_messages List recent messages in an inbox. Read list_threads List conversation threads, optionally scoped to an inbox. Read read_attachment Read an attachment as structured content: PDFs are converted to markdown (scanned pages are flagged via pages_

FAQ

Questions about AgenticEmail

How do I prevent bulk modifications through AgenticEmail? +

The AgenticEmail server has 3 write tools including create_inbox, reply_to_message, send_message. 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 AgenticEmail.

How many tools does the AgenticEmail MCP server expose? +

9 tools across 2 categories: Read, Write. 6 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on AgenticEmail? +

Register the AgenticEmail 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 AgenticEmail tool call.

Deterministic rules across all 9 AgenticEmail tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENTICEMAIL →

Instant setup, no code required.

9 AgenticEmail tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from AgenticEmail's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →