Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Close CRM 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 Close (sales-team CRM) from any AI agent: leads, contacts, opportunities, activities (calls/emails/SMS/notes), tasks, smart views and custom fields. 16 tools, API-key Basic-auth.
试试这样问
Close CRM 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 → Close CRM、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Close CRM + Gemini
Drive Close (sales-team CRM) from any AI agent: leads, contacts, opportunities, activities (calls/emails/SMS/notes), tasks, smart views and custom fields. 16 tools, API-key Basic-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:
CLOSE_API_KEY
步骤 1 — 获取凭证
close.com).
Setup:
- Sign in to Close → top-right avatar → Settings → Developer → API Keys → New API Key.
- Name it ('AnythingMCP'), copy the key (starts with
api_). SetCLOSE_API_KEY.
Authentication: HTTP Basic auth with username=API_KEY and password empty. The adapter passes Authorization: Basic base64(API_KEY:). Same as Stripe's auth model.
…(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—Close CRM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 |
|---|---|
close_get_me | Return the user the API key belongs to plus the organization context (id, name, plan, addresses) |
close_list_leads | List leads (companies) with optional query filter and pagination |
close_get_lead | Fetch one lead by ID |
close_create_lead | Create a new lead (company) |
close_update_lead | Partial-update a lead |
close_list_contacts | List contacts (people) — typically scoped to a lead via the lead_id query param |
close_create_contact | Create a contact on a lead |
close_list_opportunities | List opportunities (deals) |
close_create_opportunity | Create an opportunity (deal) |
close_update_opportunity | Update an opportunity |
close_create_note_activity | Log a free-text note on a lead (timeline) |
close_list_activities | List activities (timeline events) — call, email, sms, note, meeting, etc |
close_create_task | Create a task on a lead |
close_list_lead_statuses | List the lead status values configured on the organization (e |
close_list_opportunity_statuses | List the opportunity (pipeline stage) status values — typically active stages + won/lost terminal states |
close_list_lead_custom_fields | List the custom fields defined on leads with their IDs (cf_XYZ), types, and pick-list options |
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?
