How to Connect Odoo (MCP server) to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Odoo (MCP server), paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Odoo (MCP server) + Microsoft Copilot

Connect Claude, ChatGPT or Copilot to Odoo through Odoo's own MCP server (Odoo AI, Odoo Online saas-19.4 and Odoo 20): search any model, group and total records, list models and fields, and, when your admin allows it, create and update records. Governed by the Odoo user and the AI Tools your admin exposes.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

ODOO_URL, ODOO_MCP_API_KEY

Step 1 — Get credentials

Setting up takes about 5 minutes. You need an Odoo database that has Odoo's own MCP server: Odoo Online from version saas-19.4, or Odoo 20, with the AI app installed. Your version is shown at the bottom of Settings, and a database with an MCP server offers the MCP scope when you create an API key.

1. In Odoo, click your avatar and open My Preferences (or My Profile) → Security → Add API Key. Confirm your password and give the key a name.
2. Set Scope to MCP and choose how long the key stays valid in Expires. Odoo shows the key only once, so copy it now. Create it as a dedicated Odoo user whose access rights match what the assistant may see: the key acts as that user.
3. Paste the key into ODOO_MCP_API_KEY. It is 40 lowercase hexadecimal characters; do not add the word Bearer.
4. Put the address you open Odoo at into ODOO_URL, up to the host, for example https://mycompany.odoo.com. Leave out /odoo, /web, /mcp and the trailing slash: the connector adds /mcp itself.
5. Install the connector and run odoo_mcp_ai_tool_mcp_retrieve_initial_context: it shows the signed-in user, their time zone, the active company and every company they can switch to.

Which Odoo connector? This one is for databases with Odoo's own MCP server, where your Odoo admin decides which tools exist and which writes are allowed. For Odoo 19.0 (it has no MCP server), for Odoo.sh or your own server without it, or when you want fixed tools for partners, sales orders, invoices and products, use the Odoo connector (JSON-2 API, Odoo 19 and newer). For Odoo 14 to 18, use Odoo 14-18 (JSON-RPC).

The tools come from your database: at install AnythingMCP asks Odoo's MCP server which tools it exposes. By default these are Get Models, Get Fields, Search, Read group and MCP Retrieve initial context, all read-only, and Odoo runs them with the rights of the user who owns the key. An admin can expose more (Create Records, Update Records, menus, website and image tools) in developer mode under Settings → Technical → Server Actions, by ticking Available in MCP on the tool's Usage tab. Then open the connector here and click Discover tools. Image generation spends Odoo AI credits.

What it reads: any model the Odoo user may open, such as contacts, sales orders, invoices or products. odoo_mcp_ai_tool_get_models finds the right model, odoo_mcp_ai_tool_get_fields lists its fields, odoo_mcp_ai_tool_search finds records with an Odoo domain, and odoo_mcp_ai_tool_read_group groups and totals them by day, week, month, quarter or year: revenue per month, invoices per customer, leads per stage.

Asks before every change: no write tool is on at install. Once an administrator turns on creating or updating records, the AI shows you the records and the exact values and waits for your yes before it writes anything.

Switched off at install: odoo_mcp_ai_tool_create_records and odoo_mcp_ai_tool_update_records. Odoo hides them until an admin exposes them to MCP, and here they also install switched off, because they create records or change field values on every record that matches a domain. Turn them on per tool only when the assistant should change Odoo.

Limits: Search returns 50 records by default and at most 200 per call, so the AI pages through larger results or uses Read group for totals instead of pulling thousands of rows. The API key expires on the date you set in Expires: then create a new one and paste it in.

Common errors: 401 means the key is wrong, expired or was created without the MCP scope. 404 at /mcp means the database has no MCP server (it is older than saas-19.4, or the AI app is not installed): use the Odoo or Odoo 14-18 (JSON-RPC) connector instead. Odoo publishes Get Fields without parameters, yet the tool fails unless it gets model_name and include_description, so the AI always passes both.

The connector does not add tools your Odoo does not expose, does not go beyond the access rights of the Odoo user behind the key, and does not work with databases that have no Odoo MCP server.

Step 2 — Install the 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

Step 3 — Add the connector in Microsoft Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Odoo (MCP server) tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Available tools

Example prompts

• "What were our confirmed sales per month this year? Give me the total for each month."
• "Which customers have overdue unpaid invoices, and how much does each of them owe?"
• "Find the contact Rossi Costruzioni and show me their email, phone and salesperson."
• "Which ten products did we sell most of last quarter, by quantity?"
• "Change the email of the contact Anna Weber to [email protected]. Show me the record before you update it."

FAQ

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse