SentFromAI Email MCP for Agents
This MCP server gives AI agents native SentFromAI email capabilities through 21 tools.
Create, list, and delete inboxes.
Send, reply to, and forward email, including attachments.
Read messages, search by keyword/semantic/hybrid, and list/read threads.
Create, list, and send drafts, including scheduled drafts.
Add custom sending domains and check DNS verification status.
Create, list, and delete delivery-event webhooks.
Add, list, and delete allow/block rules for addresses or domains.
Connect through a local stdio MCP server or the hosted Streamable HTTP endpoint with API-key or OAuth authentication.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SentFromAI Email MCP for Agents send an email to bob@company.com with subject 'Hello' and body 'Just checking in'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
sentfromai-mcp
This branch prepares 0.5.0-beta.3. Use its pinned install commands only after the
release operator confirms publication; a source checkout is not a published release.
This candidate pairs with Agent Login 0.2.0-beta.4, which reports the public
agent-key fingerprint during enrollment and resume. Existing 0.5.0-beta.2
installations with their matching Agent Login beta.2 peer remain supported; upgrade
the companion and its exact peers together after the new release is verified.
Existing marketplace, Gemini, Cursor and server-directory defaults remain on the
stable mail release. The beta companion is enabled explicitly through the local
installation instructions below.
MCP server for SentFromAI — email infrastructure for AI agents.
Gives any MCP-capable agent (Claude Code, Claude Desktop, Cursor, VS Code, Gemini CLI, Codex, OpenClaw, or your own MCP host) email as native tools: create inboxes, send, reply, forward, search, read threads, manage drafts, custom domains, webhooks, and allow/block rules — 21 tools, each a thin wrapper over the SentFromAI REST API. Every tool carries MCP annotations (read-only / write / send / delete) so hosts can group them and confirm the irreversible ones.
Use an existing SentFromAI API key (sf_live_…), or follow the
agent setup guide to bootstrap an
inbox through REST when agent signup is enabled. New agent accounts can receive
and read before their human claims them; sending and other changes require that
claim. The console remains available for human signup.
Let your agent install it
Paste this into your agent (Claude Code, OpenClaw, Gemini CLI, any MCP-capable agent):
Set up email for yourself: https://docs.sentfrom.ai/agent-install.mdBootstrap uses POST /v1/agent-signups, not an MCP tool: MCP requires the key
returned by signup. Save a random Idempotency-Key before the request and reuse
it with the same body for retries within the replay window. Save the response
privately; give its claim_url only to your operator in your existing chat.
GET /v1/account reports current capabilities; POST /v1/account/claim-link
refreshes a link with the original API key. Claiming preserves the inbox and key.
Use your host's protected credential configuration. Never put a real key in
chat, shell commands, source control or logs. Configure SENTFROMAI_API_KEY in
the stdio server environment privately before starting it; examples below show
placeholders only. For hosted MCP, configure its Bearer header privately.
This onboarding flow needs the matching API and console rollout; the package
itself does not create accounts or bypass account limits.
Related MCP server: ClawAIMail
Install
Claude Code
As a plugin (asks for the key when you enable it, and adds a skill that teaches Claude email etiquette):
claude plugin marketplace add sentfromai/sentfromai-mcp
claude plugin install sentfromai@sentfromaiOr as a plain MCP server:
claude mcp add sentfromai -- npx -y sentfromai-mcp@0.4.1Claude Desktop, Cursor, Windsurf, Cline, any JSON-config host
{
"mcpServers": {
"sentfromai": {
"command": "npx",
"args": ["-y", "sentfromai-mcp@0.4.1"],
"env": { "SENTFROMAI_API_KEY": "sf_live_…" }
}
}
}Cursor one-click (then paste your key into the generated config):
Cursor and Grok Bot (plugin)
Install SentFromAI from the Cursor Marketplace; Grok Bot lists the same plugin under
Settings, Plugins. It connects to the hosted endpoint and asks for your API key on install.
To try it before it is listed, copy this repo into ~/.cursor/plugins/local/sentfromai
and reload Cursor.
VS Code
Add npx -y sentfromai-mcp@0.4.1 through VS Code's MCP configuration and enter
SENTFROMAI_API_KEY in a protected input.
Gemini CLI
gemini extensions install https://github.com/sentfromai/sentfromai-mcpGemini asks for the API key on install and keeps it in your keychain.
Codex CLI
codex mcp add sentfromai -- npx -y sentfromai-mcp@0.4.1OpenClaw
openclaw mcp add sentfromai --command npx --arg -y --arg sentfromai-mcp@0.4.1
openclaw skills install git:sentfromai/sentfromai-mcpFull guide: docs.sentfrom.ai/frameworks/openclaw.
Hosted endpoint (no install)
The same 21 tools are served over Streamable HTTP at https://api.sentfrom.ai/mcp for
hosts that only speak remote MCP (claude.ai connectors, ChatGPT apps, Meta Muse, Cursor
remote servers, MCP Inspector). Authenticate with Authorization: Bearer sf_live_…
(an x-api-key header also works), or let OAuth-capable hosts sign you in: the
endpoint publishes RFC 9728 resource metadata pointing at SentFromAI's authorization server.
claude mcp add --transport http sentfromai https://api.sentfrom.ai/mcpDirectory metadata and health checks
The registry identity is ai.sentfrom/mcp, displayed as SentFromAI Email MCP.
server.json revision 0.4.2 updates the directory title and icon while continuing
to reference the stable sentfromai-mcp@0.4.1 package and the same hosted URL.
It does not promote the optional identity beta. Registry metadata is immutable
after publication, so this revision must be published under the existing identity
before directories can import it; merging the file alone does not update a listing.
The hosted MCP endpoint requires authentication for initialization and tool
discovery. An unauthenticated POST /mcp returns 401; GET /mcp returns 405
because this stateless server uses JSON-RPC POST requests. A successful
GET /health is application liveness, not an authenticated MCP health check.
For the existing Glama connector,
claim the listing and configure Admin → Test Profile with API Key authentication,
the Authorization header, and a dedicated test account's Bearer credential in
the private credential field. Use an isolated account without customer data or
billable access. Never put its credential in this repository, registry metadata,
a public listing field, an issue, or a support message. OAuth remains available
for user connections; a monitor's private test profile is separate from them.
Glama's documented health checks
initialize the connection and discover metadata without calling tools. This
server advertises the tools capability and 21 mail tools; it does not advertise
prompts or resources. Monitors should respect those advertised capabilities.
Tools
Area | Tools | Annotation |
Inboxes |
| write · read · delete |
Messages |
| send (irreversible, open world) |
| read | |
Threads |
| read |
Drafts |
| write · send · read |
Domains |
| write · read |
Webhooks |
| write · read · delete |
Allow/block |
| write · read · delete |
Replies thread correctly (In-Reply-To/References set automatically), search
supports keyword, semantic, and hybrid modes, and sends respect the same
idempotency and suppression rules as the REST API. API failures come back as tool
results with isError and the HTTP status, so the model can read a 401 (bad key)
or 402 (plan limit) and tell you instead of retrying.
Configuration
Env var | Required | Default |
| yes | — |
| no |
|
Programmatic use
The tools are exported so you can embed them in your own MCP host or transport:
import { createServer, TOOLS, callTool, createApi } from 'sentfromai-mcp'
const server = createServer({ apiKey: process.env.SENTFROMAI_API_KEY })
await server.connect(yourTransport)Privacy
This server keeps no state and stores nothing locally. Every tool call is one HTTPS
request to api.sentfrom.ai authenticated with your API key. SentFromAI's privacy
policy: https://sentfrom.ai/privacy · terms: https://sentfrom.ai/terms.
Docs
Optional Agent Login companion
For a new human account and agent, follow the bundled SentFrom beta onboarding guide. It includes a validated configuration example, the independent human activation steps, and recovery instructions. Beta admission and first-factor activation require the advertised operator process.
The email tools and application sign-in are separate capabilities. The existing hosted mail MCP endpoint does not hold your local browser or application sessions. The new local companion adds enrollment, human approval, application sign-in, authenticated application operations and logout using the open Agent Login SDK. It targets the working draft; it is not a claim that the hosted service is already deployed or certified.
The planned beta uses agentlogin@0.2.0-beta.4, @agentlogin/mcp@0.2.0-beta.4
and sentfromai-mcp@0.5.0-beta.3. These versions are release candidates until the
release operator confirms publication. Before publication, install the matching
reviewed tarballs supplied by that operator:
npm install --save-exact /absolute/artifacts/agentlogin-0.2.0-beta.4.tgz /absolute/artifacts/agentlogin-mcp-0.2.0-beta.4.tgz /absolute/artifacts/sentfromai-mcp-0.5.0-beta.3.tgzAfter those exact versions are confirmed public, a registry installation is:
npm install --save-exact agentlogin@0.2.0-beta.4 @agentlogin/mcp@0.2.0-beta.4 sentfromai-mcp@0.5.0-beta.3Use a maintained Node.js release satisfying the companion's Node.js 22.13 minimum. The mail-only package retains its existing runtime requirement.
Create a private mode-0600 Agent Login config following the companion README. Set
the selected identity's handle to the existing inbox, enrollmentEndpoint to
the actual deployed identity service's /identity/enrollment-requests, and
enrollmentCredentialEnv to SENTFROMAI_API_KEY. Supply the latter only through
the host's protected secret configuration. Set ownerPortal to the actual human
identity service origin and ownerApprovalPath to
/identity/transactions/{transaction_id} for direct human approval links. Configure each target application
explicitly; a provider catalog does not authorize application access.
For a Git-cloned Claude plugin, install the exact companion in that checkout with
npm install --no-save @agentlogin/mcp@0.2.0-beta.4 after its publication; installing
it in an unrelated project does not make it available to this wrapper. For other
hosts, use both packages from the same npm installation directory.
For Claude plugin installations, the opt-in mcp-with-identity.json contains both
local servers. Select it as the plugin's mcpServers configuration and configure
identity_config to the absolute private config path. Other MCP hosts can add a
local server command node /absolute/package/identity-server.js with
AGENTLOGIN_MCP_CONFIG and SENTFROMAI_API_KEY in their protected environment.
Keep the existing mail-only configuration when the companion is not installed.
The skills/agent-login skill explains the tool flow. Keys and cookies remain in
the local helper's private directory. A successful sign-in authenticates that
helper; it does not authenticate a separate browser. Owner approval takes place in
the independent human interface and cannot be performed with the mail API key.
Available Tools
21 toolsadd_address_ruleAInspect
Add an allow or block rule for an email address or bare domain. Block rules are enforced on both send and receive.
Inputs: kind (required), pattern (required), direction.
add_domainAInspect
Add a custom sending domain. Returns the DNS records to add to your DNS; verification is automatic once they propagate.
Inputs: hostname (required).
create_draftAInspect
Create a draft (optionally scheduled, optionally a reply). Does not send.
Inputs: inbox_id (required), to, html, text, +3 more.
create_inboxAInspect
Create a new email inbox. Defaults to the managed mail.sentvia.ai domain.
Inputs: local_part (required), display_name.
create_webhookAInspect
Register a webhook endpoint for delivery events. The signing secret is returned once on creation — store it.
Inputs: url (required), events.
delete_address_ruleCInspect
Delete an allow/block rule.
Inputs: rule_id (required).
delete_inboxBInspect
Delete an inbox. Mail to its address stops being accepted.
Inputs: inbox_id (required).
delete_webhookCInspect
Delete a webhook endpoint.
Inputs: webhook_id (required).
forward_messageAInspect
Forward a message to new recipients in a fresh thread, quoting the original and re-attaching its files.
Inputs: to (required), message_id (required), text, from_inbox_id.
get_domainBInspect
Get a domain’s verification status and required DNS records.
Inputs: domain_id (required).
get_messageAInspect
Fetch a single message by id, including body and attachment links.
Inputs: message_id (required).
get_threadBInspect
Fetch a thread and all its messages in order.
Inputs: thread_id (required).
list_address_rulesAInspect
List allow/block rules for this tenant.
Inputs: no named parameters.
list_draftsAInspect
List drafts for this tenant.
Inputs: no named parameters.
list_inboxesAInspect
List all inboxes for this tenant.
Inputs: no named parameters.
list_threadsAInspect
List conversation threads, most recently active first.
Inputs: limit, inbox_id.
list_webhooksAInspect
List webhook endpoints (signing secrets omitted).
Inputs: no named parameters.
reply_to_messageAInspect
Reply to a message, staying in its thread (sets In-Reply-To/References automatically).
Inputs: message_id (required), html, text.
search_messagesAInspect
Search messages across the tenant. mode: keyword (default), semantic (by meaning), or hybrid. No query returns recent messages.
Inputs: mode, limit, query, inbox_id.
send_draftCInspect
Send an existing draft immediately.
Inputs: draft_id (required).
send_messageBInspect
Send a new email from one of your inboxes.
Inputs: to (required), subject (required), inbox_id (required), cc, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 21 tools
Each tool targets a distinct resource and action: webhooks, inboxes, address rules, domains, messages, threads, and drafts are all clearly separated. The send/reply/forward trio is differentiated by their descriptions, so there is no ambiguity in tool selection.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., create_inbox, list_drafts, delete_webhook). The occasional use of 'add' instead of 'create' (add_domain, add_address_rule) is a minor synonym variation, not a structural inconsistency.
With 21 tools, the server is slightly larger than the typical 3-15 range, but this is justified by the breadth of the email platform (inboxes, domains, messages, threads, drafts, webhooks, and rules). Every tool has a clear purpose, so the count feels appropriate rather than bloated.
The tool surface covers core CRUD for inboxes and webhooks, plus sending, searching, threads, and drafts. Minor gaps exist, such as no delete for drafts or domains, but these can be worked around (e.g., by recreating resources). No major lifecycle dead ends are present.
Maintenance
Related MCP Connectors
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
Hosted email for AI agents: create inboxes, send, receive, and reply over MCP with scoped API keys
Email inboxes for AI agents: send, receive, reply, search, and manage threaded email over MCP.
Hosted email MCP for AI agents with inboxes, send/receive, memory, recovery, and credits.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceAn MCP server that enables AI models to read, search, and send emails via IMAP and SMTP protocols. It supports various providers like Gmail and Outlook, allowing for tasks such as retrieving unread messages, searching by sender, and managing mailbox folders.-
- AlicenseAqualityDmaintenanceEmail infrastructure for AI agents — create inboxes, send/receive email, search messages, and manage threads via MCP tools.104 npm2MIT
- AlicenseNot gradedqualityDmaintenanceA generic IMAP and SMTP MCP server that enables AI agents to interact with email accounts for reading, searching, and sending messages. It provides high-level tools for managing email workflows like daily digests and folder organization across any standard email provider.1MIT
- AlicenseAqualityCmaintenanceAn MCP server for the PostStack email API that enables AI assistants to send transactional emails, manage contacts, handle inbound email threads, and perform deliverability checks through 84 curated tools.8418 npm1MIT