跳过安装。2 分钟内即可运行。
在 cloud.anythingmcp.com 开始免费试用，一键添加 Sellsy，然后将你的 AI 客户端（Claude、ChatGPT、Copilot 或 Cursor）指向生成的 MCP 端点。无需 Docker，无需 git clone，无需任何工程经验。
Summary
Sellsy — French CRM and invoicing: companies, contacts, opportunities, invoices, estimates, items and payments. REST API v2, OAuth 2.0 client credentials.
试试这样问
Sellsy 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 → Sellsy、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Sellsy + Gemini
Sellsy — French CRM and invoicing: companies, contacts, opportunities, invoices, estimates, items and payments. REST API v2, OAuth 2.0 client credentials.
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:
SELLSY_CLIENT_ID, SELLSY_CLIENT_SECRET
步骤 1 — 获取凭证
Getting credentials
- Sign in to Sellsy, open Paramètres → API and create an application in the developer area.
- Choose the client credentials flow — it authorises the application against your own account with no browser consent step. You receive a client id and client secret.
- Set
SELLSY_CLIENT_IDandSELLSY_CLIENT_SECRET. AnythingMCP mints and refreshes the access token on its own.
This is API v2, at https://api.sellsy.com/v2. Sellsy's v1 was an entirely different, single-endpoint RPC API — if you find an example that POSTs everything to one URL with a request parameter, that is v1 and it does not apply here.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
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—Sellsy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 |
|---|---|
sellsy_list_companies | List client companies with their name, SIRET, VAT number, address and owner |
sellsy_search_companies | Search companies with Sellsy's filter object — far more expressive than the plain list |
sellsy_get_company | Read one client company in full: addresses, contacts, tax identifiers, rating and the notes recorded against it |
sellsy_list_contacts | List individual contacts with their name, e-mail, phone, position and the company they belong to |
sellsy_list_invoices | List invoices with their number, date, due date, client, net and gross totals and payment status — the receivables view |
sellsy_search_invoices | Search invoices with Sellsy's filter object — by status, date range, client or amount |
sellsy_get_invoice | Read one invoice in full: every row with its quantity, unit price, discount and VAT, the totals and the payments applied against it |
sellsy_list_estimates | List estimates (devis) with their number, date, client, total and acceptance status — what is out with prospects and not yet won |
sellsy_list_opportunities | List CRM opportunities with their name, client, amount, funnel step and expected close date — the pipeline view |
sellsy_list_items | List catalogue items with their reference, name, unit price, VAT rate and stock tracking flag |
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?
