Vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
作者提供的说明(英文原文)
ActiveCampaign API: ~325 endpoints (v3, SMS, WhatsApp, Segments) as safety-categorized MCP tools.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
MCP_TRANSPORT, ACTIVECAMPAIGN_API_URL, ACTIVECAMPAIGN_API_TOKEN, MCP_AUTH_TOKEN标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"activecampaign": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MCP_TRANSPORT",
"-e",
"ACTIVECAMPAIGN_API_URL",
"-e",
"ACTIVECAMPAIGN_API_TOKEN",
"-e",
"MCP_AUTH_TOKEN",
"ghcr.io/ohneben/activecampaign-mcp:1.1.1"
],
"env": {
"MCP_TRANSPORT": "your-value",
"ACTIVECAMPAIGN_API_URL": "your-value",
"ACTIVECAMPAIGN_API_TOKEN": "your-value",
"MCP_AUTH_TOKEN": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add activecampaign --env MCP_TRANSPORT=your-value --env ACTIVECAMPAIGN_API_URL=your-value --env ACTIVECAMPAIGN_API_TOKEN=your-value --env MCP_AUTH_TOKEN=your-value -- docker run -i --rm -e MCP_TRANSPORT -e ACTIVECAMPAIGN_API_URL -e ACTIVECAMPAIGN_API_TOKEN -e MCP_AUTH_TOKEN ghcr.io/ohneben/activecampaign-mcp:1.1.1运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"activecampaign": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MCP_TRANSPORT",
"-e",
"ACTIVECAMPAIGN_API_URL",
"-e",
"ACTIVECAMPAIGN_API_TOKEN",
"-e",
"MCP_AUTH_TOKEN",
"ghcr.io/ohneben/activecampaign-mcp:1.1.1"
],
"env": {
"MCP_TRANSPORT": "your-value",
"ACTIVECAMPAIGN_API_URL": "your-value",
"ACTIVECAMPAIGN_API_TOKEN": "your-value",
"MCP_AUTH_TOKEN": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"activecampaign": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"MCP_TRANSPORT",
"-e",
"ACTIVECAMPAIGN_API_URL",
"-e",
"ACTIVECAMPAIGN_API_TOKEN",
"-e",
"MCP_AUTH_TOKEN",
"ghcr.io/ohneben/activecampaign-mcp:1.1.1"
],
"env": {
"MCP_TRANSPORT": "your-value",
"ACTIVECAMPAIGN_API_URL": "your-value",
"ACTIVECAMPAIGN_API_TOKEN": "your-value",
"MCP_AUTH_TOKEN": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 ohneben 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:MCP_TRANSPORT, ACTIVECAMPAIGN_API_URL, ACTIVECAMPAIGN_API_TOKEN, MCP_AUTH_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.1.1)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。
同一分类中有:Vexa, emailmd, MCP WhatsApp Cloud
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
MCP server for WhatsApp Cloud API (Meta) — messages, media, and templates via Graph API
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
The most complete ActiveCampaign MCP server there is. Run your entire ActiveCampaign account in plain language from Claude, Cursor, or any other MCP client.
This Model Context Protocol server exposes the whole ActiveCampaign account API — ~325 tools — covering the v3 REST API plus the SMS, WhatsApp and async Segments APIs, generated straight from ActiveCampaign's own OpenAPI definitions. Every tool is safety-categorized (🟢 read-only / 🟡 write / 🔴 destructive) so your assistant knows what an action does *before* it calls it. It runs over stdio (Claude Desktop and other local launchers) or Streamable HTTP (hosted in Docker), and ships with retries, client-side rate limiting tuned to ActiveCampaign's 5 req/s cap, and request timeouts so it holds up against a live account.
Some MCP servers just forward a slice of the API. This one is built to be safe to hand to an LLM, complete, and easy to run for real:
| What you get | Why it matters |
|---|---|
| ~325 tools — the full account API | Complete coverage of contacts, deals, accounts, lists, tags, custom fields & objects, ecommerce (deep data), campaigns, messages, automations, segments, webhooks, tasks, calendars, site/event tracking, SMS and WhatsApp — nothing hand-picked or left behind. Other servers stop at ~60. |
| Curated safety categories 🟢 / 🟡 / 🔴 | Not naive "GET = safe": contact sync is flagged as an upsert, a segment-match POST as a read-only query, tagging a contact as a link, and POST /sms/broadcasts as sends messages — so the model knows the real blast radius. |
Machine-readable MCP annotations (readOnlyHint, destructiveHint) | Hosts that honor annotations (Claude included) can auto-trust reads and demand confirmation before anything destructive. |
| Read-only mode & resource filtering | Expose only 🟢 read-only tools (ACTIVECAMPAIGN_READ_ONLY=true), or narrow to just the groups you use (ACTIVECAMPAIGN_INCLUDE_GROUPS=contacts,deals,lists). Tailor the surface per deployment. |
| Pagination made first-class | limit, offset, orders[…] and filters[…] are injected onto every list endpoint as typed inputs, so the assistant can page, sort and filter without guessing ActiveCampaign's bracket syntax. |
| Automatic retries with backoff | Transient 429 / 5xx responses are retried with jittered exponential backoff, honoring the server's Retry-After header. |
| Built-in rate limiting | Self-throttles under ActiveCampaign's 5 requests / second account cap so a burst of tool calls never trips a 429. |
| Response-size guard | Optionally cap huge list responses (ACTIVECAMPAIGN_MAX_RESPONSE_CHARS) so one call can't blow the model's context window. |
| GraphQL passthrough | A bonus tool for ActiveCampaign's Ecommerce GraphQL API when you want to shape exactly the fields you need in one round-trip. |
| **Two transports: stdio *and* Streamable HTTP** | Use it locally in Claude Desktop, or run one always-on server that any number of MCP clients reach over HTTP. |
| Docker + docker-compose, health check, auto-restart | Production-style deployment out of the box: docker compose up and it stays up. |
| Optional bearer-token auth on the HTTP endpoint | Put the server behind a shared secret the moment it's reachable beyond localhost. |
| Your token never reaches the model | The Api-Token lives in the server's environment and is injected on every request — the assistant only ever sees tool inputs and API responses. |
| Drop-in spec updates | ActiveCampaign ships newer OpenAPI JSON? Replace the file in spec/ and rebuild — new endpoints become new tools automatically, no code changes. |
There are a few ways to reach ActiveCampaign from an AI assistant today. Here's how this server stacks up against the alternatives:
| This server | Official AC remote MCP | HighLiuk mcp-server-activecampaign | mcp-activecampaign (PyPI) | CData MCP | |
|---|---|---|---|---|---|
| Approx. tools | ~325 | curated subset | 58 | ~65 | 3 (generic SQL) |
| Full v3 REST coverage | ✅ | ➖ | ➖ core CRM | ➖ broad CRM | ❌ |
| SMS · WhatsApp · Segments | ✅ | ❌ | ❌ | ❌ | ❌ |
| Ecommerce deep data + GraphQL | ✅ | ➖ | ❌ | ➖ | ❌ |
| Reads and writes | ✅ | ✅ | ✅ | ✅ | ❌ read-only |
| Self-hosted on your own infra | ✅ | ❌ vendor cloud | ✅ | ✅ | ✅ |
| Connects directly to the AC API | ✅ | ✅ | ✅ | ✅ | ❌ via JDBC driver |
stdio transport | ✅ | ❌ | ✅ | ✅ | ✅ |
| Streamable-HTTP transport | ✅ | ✅ | ➖ | ➖ | ❌ |
| Docker + compose + health check | ✅ | n/a | ❌ | ❌ | ❌ |
| Curated 🟢 / 🟡 / 🔴 safety categories | ✅ | ➖ | ➖ partial | ➖ | n/a |
readOnlyHint / destructiveHint | ✅ | ➖ | ➖ | ➖ | ➖ |
| Read-only mode + group filtering | ✅ | ❌ | ❌ | ❌ | always read-only |
Rate limiting + auto-retry (429/5xx) | ✅ | ➖ | ❌ | ➖ | ❌ |
| Language | TypeScript | — | TypeScript | Python | Java |
| License | MIT | proprietary | MIT | MIT | MIT |
✅ = yes · ➖ = partial / not documented · ❌ = no. Compiled from each project's public documentation; this is an unofficial project, not affiliated with ActiveCampaign or the projects listed. Tool counts are approximate and move as APIs evolve.
The short version: the official remote MCP is a great managed on-ramp but runs in ActiveCampaign's cloud on a curated slice of the API. The community servers are solid but top out around 60 tools of core CRM, stdio-only, without a deployment story. This one gives you the entire account API, both transports, a Docker deployment, and safety guardrails — self-hosted, on your token, MIT.
Once it's connected, ask your assistant things like:
Tools are generated automatically from ActiveCampaign's specs and grouped into 🟢 read-only, 🟡 write and 🔴 destructive — so a well-behaved host can treat each group differently.
Claude / Cursor / any MCP client ──MCP──► this server ──HTTPS──► ActiveCampaign API (your account)
The server parses the bundled OpenAPI definitions into MCP tools (resolving $refs and guarding against recursive schemas), tags each with a curated safety category, and injects your Api-Token header on every outgoing request. Your token stays in the server's environment — the model never sees or handles it.
1. Add your credentials. Copy the example config and fill it in:
cp .env.example .env
2. Start the server:
docker compose up -d --build
The bundled docker-compose.yml binds to 127.0.0.1:8765 only, so the server is reachable from your machine but not the network.
3. Confirm it's running:
curl -s http://localhost:8765/health
4. Connect your MCP client. The MCP endpoint is http://localhost:8765/mcp.
mcp-remote. Add this under mcpServers in your config, then fully quit and reopen the app: {
"mcpServers": { "activecampaign": { "command": "npx", "args": [ "mcp-remote", "http://localhost:8765/mcp", "--header", "Authorization: Bearer YOUR_MCP_AUTH_TOKEN" ] } } }
(Drop the --header line if you left MCP_AUTH_TOKEN empty.)
claude mcp add --transport http activecampaign http://localhost:8765/mcp
Every push to main publishes a ready-to-run image to the GitHub Container Registry, so you can skip the local build entirely:
docker run -d --name activecampaign-mcp -p 127.0.0.1:8765:8765 --env-file .env \
ghcr.io/ohneben/activecampaign-mcp:latest
ACTIVECAMPAIGN_API_URL. It looks like https://your-account.api-us1.com/api/3. Use the exact URL shown — not all accounts are on api-us1, and custom domains differ.ACTIVECAMPAIGN_API_TOKEN.Put both in .env. The server injects the token on every request, so your assistant never sees it.
Everything is set in .env (copied from .env.example):
| Variable | Required | Default | Description |
|---|---|---|---|
ACTIVECAMPAIGN_API_URL | ✅ | — | Your account's API URL, incl. /api/3 |
ACTIVECAMPAIGN_API_TOKEN | ✅ | — | Your API token (Api-Token header) |
MCP_TRANSPORT | — | stdio | stdio or http (the Docker image defaults to http) |
PORT | — | 8765 | HTTP listen port |
HOST | — | 0.0.0.0 | HTTP bind address |
MCP_HTTP_PATH | — | /mcp | HTTP MCP route |
MCP_AUTH_TOKEN | — | _(off)_ | Require Authorization: Bearer on /mcp |
ACTIVECAMPAIGN_MAX_REQUESTS | — | 4 | Client-side requests per window (0 disables throttling) |
ACTIVECAMPAIGN_RATE_WINDOW_MS | — | 1000 | Rate-limit window in ms (default: 4 req/s) |
ACTIVECAMPAIGN_MAX_RETRIES | — | 3 | Retries on 429 / 5xx / network errors |
ACTIVECAMPAIGN_TIMEOUT_MS | — | 30000 | Per-attempt request timeout |
| ACTIVECAMPAIGN_READ_ONLY | — | false | Expose only 🟢 read-only to
只显示了开头部分;其余内容请在仓库中阅读