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 Odoo,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。
摘要
通过 JSON-2 API 访问 Odoo ERP:搜索、读取、创建和更新任何模型,另外还提供面向合作伙伴、销售订单、发票和产品的专用工具。适用于 Odoo Online、Odoo.sh 和自托管的 Odoo 19+,bearer API key。
试试这样问
Odoo 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 → Odoo、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Odoo + Gemini
通过 JSON-2 API 访问 Odoo ERP:搜索、读取、创建和更新任何模型,另外还提供面向合作伙伴、销售订单、发票和产品的专用工具。适用于 Odoo Online、Odoo.sh 和自托管的 Odoo 19+,bearer API key。
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:
ODOO_URL, ODOO_DB, ODOO_API_KEY
步骤 1 — 获取凭证
Getting an API key
- In Odoo open your user menu → My Profile → Account Security and create a new API key. Odoo shows it once.
- Put it in
ODOO_API_KEY, your instance URL inODOO_URL(e.g.https://mycompany.odoo.com, no trailing slash) and the database name inODOO_DB. On Odoo Online the database name is usually the subdomain.
…(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
你的服务器 URL: 在 AnythingMCP 中打开 MCP Servers → 此连接器所在的服务器,复制它的 URL(
https://cloud.anythingmcp.com/mcp/…)。本指南中出现YOUR_SERVER_ID的地方都用它替换。
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/YOUR_SERVER_ID",
"headers": { "X-API-Key": "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—Odoo应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID传入请求的tools数组,使用相同的X-API-Key请求头。
可用工具
| Tool | What it does |
|---|---|
odoo_search_read | Search and read any Odoo model in one call |
odoo_read | Read specific records of a model by their ids — the follow-up call when a search has returned ids and you now want the detail of a few of th |
odoo_search_count | Count the records of a model matching a domain, without transferring them |
odoo_fields_get | Describe a model's fields: name, type, label, whether it is required or readonly, and the related model for relational fields |
odoo_list_partners | List partners — Odoo's customers, suppliers and contacts — with name, e-mail, phone, city and country |
odoo_list_sale_orders | List sales orders with their customer, date, state and total |
odoo_list_invoices | List customer invoices and vendor bills with their partner, date, due date, state and residual amount — the answer to 'what is still unpaid' |
odoo_list_products | List products with their internal reference, sale price, cost, on-hand quantity and product type |
odoo_create | Create a record in any Odoo model |
odoo_write | Update existing records in any Odoo model |
odoo_call_method | Call an arbitrary public method on an Odoo model — the escape hatch for workflow actions such as action_confirm on a sale order or action_po |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带自定义请求头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?