Skip to content

SendForAI MCP server

com.sendforai/mcpsendforai.comstreamable-httpv0.1.2Scanned

Transactional and broadcast email at cost. Your agent signs up, tests and sends; no API key.

23 tools: 1 can delete or cancel things, 4 do something that can't be undone, 8 change things and 10 only read.

Tools: 1 delete, 4 irreversible, 8 write, 10 read.
  • Reads private data · 4
  • Reads text others write · 4
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 4 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the SendForAI MCP server can do

The SendForAI MCP server is published by sendforai.com, a domain the MCP Registry verified. It has 23 tools. It can delete or cancel things (1 tool: cancel_broadcast), do things that cannot be undone, such as sending, paying or publishing (plan_email, send_email, create_broadcast and send_broadcast) and create or change data (8 tools: verify_domain, add_domain, upsert_contact, import_contacts and 4 more). 10 tools only read.

4 tools read private data (get_capacity, get_usage, list_contacts and 1 more); 4 tools bring in text other people can write (get_capacity, get_usage, get_broadcast and 1 more); 4 tools can send data out of your system (plan_email, send_email, create_broadcast and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 18, 2026, version 0.1.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

23 tools

Deletes or cancels 1Claude Code: deny
  • cancel_broadcastCancel a broadcast before or during sending.No findings

    Why it is in this group

    • The name "cancel_broadcast" says "cancel": a word for removing or ending something.
    Description, as the server wrote it
    Cancel a broadcast before or during sending. Emails already sent stay sent; the unsent remainder is cancelled.
Can't be undone 4Claude Code: ask
  • create_broadcastCreate a broadcast to subscribed contacts (optionally filtered by contact data).Can send data outNo findings

    Why it is in this group

    • The name "create_broadcast" says "create": a word for a change.
    • The name "create_broadcast" also says "broadcast": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "create_broadcast" says "broadcast": it sends or publishes something to other people.
    Description, as the server wrote it
    Create a broadcast to subscribed contacts (optionally filtered by contact data). By default it waits for a human: the response includes approval_url. Hand that link to your operator; clicking it sends. Use dry_run to see recipients, cost, and lint first.
  • plan_emailEverything send_email does except sending.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Everything send_email does except sending. Returns cost, capacity after send, suppression hits, and lint warnings with fixes. Call this before send_email when cost or deliverability matters.
  • send_broadcastStarts sending an approved broadcast in the background (status: sending).Can send data outNo findings

    Why it is in this group

    • The name "send_broadcast" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_broadcast" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Starts sending an approved broadcast in the background (status: sending). Poll get_broadcast for progress. Large Member broadcasts continue after the daily cap resets. Returns a 409 with the approval_url if a human has not approved it yet.
  • send_emailSend a transactional email from the configured domain.Can send data outNo findings

    Why it is in this group

    • The name "send_email" says "send": a word for sending, and what is sent cannot be taken back.
    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe name "send_email" says "send": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Send a transactional email from the configured domain. Response includes id, cost, capacity, lint, and a signed receipt.
Changes things 8Claude Code: ask
  • add_creditReturns a checkout_url for your human operator to add prepaid credit (minimum $10).No findings

    Why it is in this group

    • The name "add_credit" says "add": a word for a change.
    Description, as the server wrote it
    Returns a checkout_url for your human operator to add prepaid credit (minimum $10). Use it when a send returns balance_required. $5 is taken only in months you send to anyone outside your own domains (10,000 emails included), then $0.11/1k at cost. Pass auto_topup: true to let their saved card refill the balance automatically, always within the budget they set. Never pay it yourself; hand the link over. account.topped_up appears in list_events when they finish.
  • add_domainLet this account send from another domain with the same key.No findings

    Why it is in this group

    • The name "add_domain" says "add": a word for a change.
    Description, as the server wrote it
    Let this account send from another domain with the same key. First publish DNS TXT _sendforai.<domain> = "v=sfa1; delegate=<identity domain>" (if you have DNS access) or hand that record to your operator, then call this. If the record is not visible yet the response says exactly what to publish. Up to 50 domains, no fee; each keeps its own reputation and warmup.
  • billing_portalA Stripe billing portal link for your operator: update the saved card and download receipts.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    A Stripe billing portal link for your operator: update the saved card and download receipts.
  • import_contactsBulk import up to 10,000 contacts per call, deduplicated by email.No findings

    Why it is in this group

    • The name "import_contacts" says "import": a word for a change.
    Description, as the server wrote it
    Bulk import up to 10,000 contacts per call, deduplicated by email. Available in a sending month; on the free build tier the error explains what to do.
  • set_auto_topupTurn auto top-up off, or change its amount.No findings

    Why it is in this group

    • The name "set_auto_topup" says "set": a word for a change.
    Description, as the server wrote it
    Turn auto top-up off, or change its amount. Turning it on requires a saved card from a human-completed add_credit.
  • set_budgetLowering the budget applies immediately.No findings

    Why it is in this group

    • The name "set_budget" says "set": a word for a change.
    Description, as the server wrote it
    Lowering the budget applies immediately. Raising it returns an approval_url that only your human operator can approve; hand it over. Use when a send returns budget_exceeded.
  • upsert_contactStore a contact for broadcasts.No findings

    Why it is in this group

    • The name "upsert_contact" says "upsert": a word for a change.
    Description, as the server wrote it
    Store a contact for broadcasts. Contacts are unlimited on every plan. Data is arbitrary JSON you can filter on later.
  • verify_domainCreate the SES identity for a domain on this account (default: the configured identity domain) and return the DKIM and MAIL FROM records to publish.No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create the SES identity for a domain on this account (default: the configured identity domain) and return the DKIM and MAIL FROM records to publish. Idempotent; call again to re-check.
Only reads 10Show 10 read-only tools
  • get_accountBalance, whether this month's $5 sending fee is paid, auto top-up, the monthly usage budget (used and remaining), emails used and included remaining, and every sending domain.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_account" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Balance, whether this month's $5 sending fee is paid, auto top-up, the monthly usage budget (used and remaining), emails used and included remaining, and every sending domain. Check this before a large send.
  • get_broadcastStatus, cost, approval_url (while awaiting approval), and progress (sent, queued, failed, cancelled, resumes_at) once sending starts.Reads text others writeNo findings

    Why it is in this group

    • The name "get_broadcast" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "status" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Status, cost, approval_url (while awaiting approval), and progress (sent, queued, failed, cancelled, resumes_at) once sending starts.
  • get_capacityHow many emails can be sent right now: daily cap, sent today, remaining, warmup stage, and when the window resets.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_capacity" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    How many emails can be sent right now: daily cap, sent today, remaining, warmup stage, and when the window resets.
  • get_domain_statusIdentity, SES verification status, DNS records still needed, and current sending capacity for the configured domain.No findings

    Why it is in this group

    • The name "get_domain_status" says "get": a word for reading.
    Description, as the server wrote it
    Identity, SES verification status, DNS records still needed, and current sending capacity for the configured domain.
  • get_pricingPublic, machine-readable pricing.No findings

    Why it is in this group

    • The name "get_pricing" says "get": a word for reading.
    Description, as the server wrote it
    Public, machine-readable pricing. Use it to compute cost before committing to a send.
  • get_usageEmails sent this period, SES cost, what has been billed, included allowance remaining, and a projection to period end.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Emails sent this period, SES cost, what has been billed, included allowance remaining, and a projection to period end.
  • list_contactsPage through contacts.Reads private dataNo findings

    Why it is in this group

    • The name "list_contacts" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_contacts" says "list" and "contact": it reads contacts.
    • private-dataThe description's first sentence says "contact": it reads contacts.
    Description, as the server wrote it
    Page through contacts.
  • list_domainsEvery domain this account can send from, with role (identity or delegated), status, SES status, warmup stage and daily cap.No findings

    Why it is in this group

    • The name "list_domains" says "list": a word for reading.
    Description, as the server wrote it
    Every domain this account can send from, with role (identity or delegated), status, SES status, warmup stage and daily cap.
  • list_eventsPull delivery, bounce, complaint, broadcast, and unsubscribe events by cursor.No findings

    Why it is in this group

    • The name "list_events" says "list": a word for reading.
    Description, as the server wrote it
    Pull delivery, bounce, complaint, broadcast, and unsubscribe events by cursor. No webhook endpoint needed. Keep next_cursor between calls.
  • whoamiThe identity this server acts as, how it authenticates, and whether it is a sandbox.No findings

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.
    Description, as the server wrote it
    The identity this server acts as, how it authenticates, and whether it is a sandbox.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

64 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 4 outbound tools breaks every one.

Reads private data4
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__sendforai__create_broadcast",
      "mcp__sendforai__plan_email",
      "mcp__sendforai__send_broadcast",
      "mcp__sendforai__send_email"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 21, 2026, 19:20 UTC, unchanged since Nov 21, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
14
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 14 tools that change things (1 destructive, 4 irreversible, 9 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://sendforai.com/mcp: tools/list returned 24 tools to an anonymous client, including cancel_broadcast (destructive), plan_email (irreversible), send_email (irreversible), create_broadcast (irreversible), send_broadcast (irreversible) and 9 more

    What this check looks for

Posture changes

  1. Nov 21, 2026
    • Tools that change things, listed without credentials: 13 to 14

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 13 -> 14.View diff
    • Tools that change things, listed without credentials: 13 to 14

Install

Pinned to version 0.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http sendforai https://sendforai.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http sendforai https://sendforai.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__sendforai__get_pricing",
      "mcp__sendforai__get_domain_status",
      "mcp__sendforai__list_domains",
      "mcp__sendforai__get_capacity",
      "mcp__sendforai__get_usage",
      "mcp__sendforai__list_contacts",
      "mcp__sendforai__get_broadcast",
      "mcp__sendforai__get_account",
      "mcp__sendforai__list_events",
      "mcp__sendforai__whoami"
    ],
    "ask": [
      "mcp__sendforai__verify_domain",
      "mcp__sendforai__add_domain",
      "mcp__sendforai__plan_email",
      "mcp__sendforai__send_email",
      "mcp__sendforai__upsert_contact",
      "mcp__sendforai__create_broadcast",
      "mcp__sendforai__send_broadcast",
      "mcp__sendforai__import_contacts",
      "mcp__sendforai__add_credit",
      "mcp__sendforai__set_budget",
      "mcp__sendforai__set_auto_topup",
      "mcp__sendforai__billing_portal"
    ],
    "deny": [
      "mcp__sendforai__cancel_broadcast"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as sendforai. Review it before you use it.

Capability tags behind 9 rules
  • mcp__sendforai__get_capacity private-data, untrusted-input
  • mcp__sendforai__get_usage private-data, untrusted-input
  • mcp__sendforai__plan_email outbound
  • mcp__sendforai__send_email outbound
  • mcp__sendforai__list_contacts private-data
  • mcp__sendforai__create_broadcast outbound
  • mcp__sendforai__get_broadcast untrusted-input
  • mcp__sendforai__send_broadcast outbound
  • mcp__sendforai__get_account private-data, untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.sendforai/mcp/verify?hash=c8a24554f874530bb957f6bade0ff35b45a0a710277c2cea0093070882eeee35" | jq -e '.changed == false'

Pinned hash c8a24554f874, from Nov 18, 2026, 01:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.sendforai/mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.sendforai/mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/com.sendforai/mcp.svg)](https://radar.anlyon.com/servers/com.sendforai/mcp)

Source: MCP Registry. Synced Nov 18, 2026, 02:17 UTC.

SendForAI MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the SendForAI MCP server safe?

No scan can promise that. What its definitions show: 23 tools, 13 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the SendForAI MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: cancel_broadcast.

Can the SendForAI MCP server do things that cannot be undone?

Yes. 4 tools can send, pay, publish or merge: plan_email, send_email, create_broadcast and send_broadcast.

What tools does the SendForAI MCP server have?

23 tools: 1 destructive, 4 irreversible, 8 write, 10 read. cancel_broadcast, plan_email, send_email, create_broadcast, send_broadcast, verify_domain, add_domain, upsert_contact and 15 more.

Does the SendForAI MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the SendForAI MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): plan_email, send_email, create_broadcast and send_broadcast.

Has the SendForAI MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.