Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Kustomer in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Drive Kustomer (modern customer service CRM, Meta-owned) from any AI agent: conversations, messages, customers, notes, custom objects. 10 tools, Bearer auth.
试试这样问
Kustomer 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Kustomer、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Kustomer + Gemini
Drive Kustomer (modern customer service CRM, Meta-owned) from any AI agent: conversations, messages, customers, notes, custom objects. 10 tools, Bearer auth.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
KUSTOMER_API_KEY, KUSTOMER_SUBDOMAIN
步骤 1 — 获取凭证
kustomer.com).
Setup:
- Sign in to Kustomer → top-right avatar → Settings → Security → API Keys → Add API Key.
- Pick role: org.permission.customer.read+write, org.permission.conversation.read+write, etc.
- Set
KUSTOMER_API_KEY. - Note your org subdomain (e.g.
acmeforacme.kustomerapp.com). SetKUSTOMER_SUBDOMAIN.
Authentication: Authorization: Bearer ${KUSTOMER_API_KEY}.
Subdomain-templated URL: https://${KUSTOMER_SUBDOMAIN}.api.kustomerapp.com/v1.
Customer-centric model: Kustomer's selling point is the unified customer timeline. A customer has multiple emails/phones/social handles; conversations roll up under the customer.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Kustomer应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
kustomer_get_current_tracking_id | Return the org / org details — sanity check for API key validity |
kustomer_search_customers | Search customers via the v1 search endpoint (Kustomer's Lucene-style query) |
kustomer_get_customer | Fetch a customer by ID |
kustomer_create_customer | Create a customer |
kustomer_search_conversations | Search conversations |
kustomer_get_conversation | Fetch a conversation by ID |
kustomer_update_conversation | Update a conversation — change status (open/snoozed/done), assignee, queue, priority, tags |
kustomer_add_note_to_conversation | Add an internal note (private — not sent to customer) |
kustomer_create_outbound_message | Send a public message in a conversation (email/SMS/chat reply) |
kustomer_list_users | List org users (agents) |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
