Sendsets
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Sendsets: the cold email API for AI agents
Sendsets gives AI agents a programmable way to run cold email. An agent (Claude Code, Codex, Cursor, Gemini CLI, ChatGPT, or your own code) can connect sending mailboxes, warm them up, build and launch outbound campaigns, add leads, and read and answer replies through an MCP server, a CLI, or a REST API instead of a sales dashboard.
This repository is the public, agent-facing home of Sendsets:
What | Where |
Remote MCP server |
|
Agent skills ( |
|
Claude Code plugin marketplace | |
Codex plugin marketplace | |
Agent Plugins manifest | |
Gemini CLI extension | |
MCP Registry manifest |
|
OpenAPI 3.1 spec | |
Docs |
Sign up at app.sendsetsapi.com. Free for up to 10 mailboxes.
What an agent can do with it
The MCP server and the REST API expose the same service-layer tools. What a credential can see is limited by the scopes it was granted.
Campaigns: create a draft, add and edit sequence steps, pick sender mailboxes, view leads, logs and stats, start and stop
Leads and contacts: add, search, tag, bulk edit, read timelines and sent mail, manage segments
Mailboxes: list and inspect connected mailboxes, adjust limits, toggle warmup, set tracking domains, check warmup standing
Inbox and replies: list and read threads, draft and send replies, label, snooze, cancel scheduled sends
Runs: durable, idempotent, preflighted campaign runs (
create_run,get_run,list_runs,cancel_run)Suppressions, analytics, webhooks: manage the do-not-contact list, read dashboard analytics, manage signed webhooks
Send-class tools (start_campaign, compose_email, send_reply, and an autonomous create_run) go through a credential-bound policy. A call returns executed, awaiting_approval (a person approves it in the dashboard within 30 minutes), or blocked. Approval can never override a missing opt-out, a suppression, or a mailbox health check.
Related MCP server: MuntuAI MCP
Connect the MCP server
The server advertises OAuth 2.1 protected-resource metadata (RFC 9728) and supports dynamic client registration, so MCP clients that speak OAuth sign you in through the browser with no key to paste. A static ssk_ API key from the dashboard works too, as Authorization: Bearer ssk_....
Claude Code
claude mcp add --transport http sendsets https://api.sendsetsapi.com/v1/mcpOr install the plugin, which adds the MCP server and the skills together:
/plugin marketplace add AddisonHoff/sendsets
/plugin install sendsets@sendsetsClaude (claude.ai and Claude Desktop): Settings > Connectors > Add custom connector, URL https://api.sendsetsapi.com/v1/mcp.
Codex
codex plugin marketplace add AddisonHoff/sendsets # MCP server + skills as a pluginor just the MCP server:
codex mcp add sendsets --url https://api.sendsetsapi.com/v1/mcp
codex mcp login sendsetsCursor (~/.cursor/mcp.json)
{
"mcpServers": {
"sendsets": { "url": "https://api.sendsetsapi.com/v1/mcp" }
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"sendsets": { "type": "http", "url": "https://api.sendsetsapi.com/v1/mcp" }
}
}Gemini CLI
gemini extensions install https://github.com/AddisonHoff/sendsetsAny client with a static key
{
"mcpServers": {
"sendsets": {
"type": "http",
"url": "https://api.sendsetsapi.com/v1/mcp",
"headers": { "Authorization": "Bearer ssk_..." }
}
}
}Install the skills
send-cold-email is the direct path: take a lead list and send a cold email sequence with follow-ups, from mailbox check to launch and replies. The sendsets skill teaches an agent to read your product, propose five outbound workflows that use the product itself, then build and run the one you pick. The sendsets-cli skill is the full reference for driving Sendsets from a terminal.
npx skills add AddisonHoff/sendsetsOr copy skills/sendsets into ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex). The same files are served at https://sendsetsapi.com/skills/sendsets/SKILL.md, and https://sendsetsapi.com/claude.md is a one-link starting point for any coding agent.
CLI
brew install addisonhoff/tap/sendsets # macOS, Linux
sendsets login --hostname sendsetsapi.com
sendsets doctor --jsonWindows: scoop bucket add sendsets https://github.com/AddisonHoff/homebrew-tap, then scoop install sendsets. Archives and checksums.txt for every platform are on sendsets-releases. The CLI signs in as a person and speaks only the public REST API; every command takes --json.
REST API
Base URL https://api.sendsetsapi.com/v1. Errors carry a stable code and request_id, lists use data plus cursor pagination, and side-effectful writes accept an Idempotency-Key. Spec: openapi.json. Reference: docs.sendsetsapi.com/api.
What this plugin connects to
The MCP server at
https://api.sendsetsapi.com/v1/mcp, over HTTPS, authenticated with your own OAuth sign-in or API key. Every tool call reads or changes data in your Sendsets workspace; send tools deliver real email from your connected mailboxes.The skills may tell the agent to install the
sendsetsCLI with Homebrew or Scoop from AddisonHoff/homebrew-tap, or from a release archive checked against its publishedchecksums.txt. The CLI talks only tohttps://api.sendsetsapi.com.Nothing else. The plugin has no hooks, no local server and no scripts that run on install, and its MCP configuration never reads credentials from your environment.
Safety defaults
Sendsets is conservative by default: 50 campaign emails per mailbox per day, 600 seconds between sends from one mailbox, gradual warmup, automatic suppression on bounces, complaints and unsubscribes, and a stop on reply. A test send and a live launch are separate decisions, and an agent should not launch a campaign unless the user asked it to send.
License
The skills and manifests in this repository are licensed under Apache-2.0.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Hosted email for AI agents: create inboxes, send, receive, and reply over MCP with scoped API keys
Email infrastructure for AI agents — send, receive, search, and reply to email over MCP.
AI agent platform: manage leads, conversations, bots, calendar and CRM via MCP.
Run cold email outbound from an AI agent: campaigns, leads, replies, sender accounts, autopilot.
Related MCP Servers
- AlicenseAqualityBmaintenanceAgent-native cold-email infrastructure providing ~12 high-level tools for domain setup, mailbox provisioning, campaign launch, inbox management, and metrics, all operated via MCP or CLI.281MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to programmatically manage email outreach campaigns, leads, domains, senders, and webhook events, as well as send emails, through the Model Context Protocol over HTTP.-
- FlicenseBqualityCmaintenanceEnables external AI agents to read, send, and manage email over IMAP/SMTP via MCP, including inbox listing, search, drafts, scheduled/batch sending, and operations like reply, archive, and labels.303-

LinkedCamp MCP serverofficial
AlicenseNot gradedqualityBmaintenanceEnables building and launching LinkedIn and email outreach campaigns, authoring multi-step sequences, triaging a unified inbox, managing prospects and sending accounts, and pulling client reports directly from AI assistants and MCP clients.MIT