instantly-mcp
MCP server for Instantly.ai, allowing Claude to query campaign analytics, warmup health, and sending accounts, and to manage campaigns and replies with confirmation.
README
instantly-mcp
A local stdio MCP server that exposes the Instantly.ai v2 API to Claude Code — the same way crmdata exposes HubSpot, but with no dashboard, no database, no hosting. Just the tools.
Claude Code ──stdio──▶ node src/server.mjs ──HTTPS+Bearer──▶ Instantly v2 API
Setup
cd instantly-mcp
npm install
cp .env.example .env # then paste your INSTANTLY_API_KEY
npm run smoke # boots the server, lists tools, does one live read
Get the key from Instantly → Settings → Integrations → API keys.
Wire it into Claude Code
Use absolute paths (stdio launches the process directly):
claude mcp add instantly -- node --env-file="C:/Users/colen/OneDrive/Desktop/Code-Projects/instantly-mcp/.env" "C:/Users/colen/OneDrive/Desktop/Code-Projects/instantly-mcp/src/server.mjs"
Verify:
claude mcp list
Then just ask, in any Claude Code session:
"How are my Instantly campaigns doing this week, and is any sending account's warmup health dropping?"
Tools
Read
| Tool | What it does |
|---|---|
list_campaigns |
Campaigns with ids, names, status |
get_campaign_analytics |
Sent/open/reply stats (one campaign or all) |
list_accounts |
Connected sending inboxes |
warmup_analytics |
Inbox-vs-spam + 0–100 health per account |
account_vitals |
SPF/DKIM/DMARC deliverability checks |
list_emails |
Unibox (address or thread:<id>) |
get_email |
One email, full body |
unread_count |
Unread count |
list_leads_in_campaign |
Leads on a campaign |
Write — staging (no send)
| Tool | What it does |
|---|---|
create_campaign |
Create a sequence + schedule (does not launch) |
add_leads |
Bulk-add leads to a campaign |
mark_thread_read |
Mark a unibox thread read |
Write — LIVE SEND (require confirm: true)
| Tool | What it does |
|---|---|
activate_campaign |
Launches a campaign — it starts sending |
reply_to_email |
Sends a reply into a unibox thread |
The two live-send tools refuse unless you pass confirm: true, so cold email is never fired on a one-word ask.
Files
src/client.mjs thin Instantly v2 fetch wrapper (zero deps)
src/tools.mjs tool definitions (name, description, zod schema, handler)
src/server.mjs McpServer + stdio transport
scripts/smoke.mjs end-to-end boot + tools/list test
Notes
- All 9 read tools are verified live against the real workspace (2026-07-17). Two endpoints ported from salesintel were stale against the current v2 API and were corrected here: warmup is
POST /accounts/warmup-analytics(hyphen), and vitals takes{ accounts: [...] }and returns per-domain MX/SPF/DKIM/DMARC.client.mjstags each endpoint[verified]/[ported]. - The 5 write tools (
create_campaign,add_leads,mark_thread_read,activate_campaign,reply_to_email) are not exercised by the smoke test — they create/send.list_leads_in_campaignshares the/leads/listpath withadd_leadsand is verified, but confirm the add shape on your first real use. - This repo does the querying; the
salesintelapp still owns durable infra (webhooks, reply polling, warmup ramp). Two views on one Instantly account, not two sources of truth.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。