3 Ways to Integrate Odoo and Hermes Agent

Method 1: Direct API Integration (XML-RPC)

The simplest approach. You create a dedicated Odoo user with restricted permissions, paste the connection details into Hermes, and your agent calls the Odoo XML-RPC API directly.

How it works: Hermes Agent has built-in Odoo tool support. When you configure the connection once, the agent can search, read, create, write, and unlink records on any Odoo model — CRM leads, partners, products, sales orders, invoices, and more.

Setup

1. Create an Odoo API key — in your Odoo instance, generate a new API key under Settings → Users → Technical
2. Set the Hermes Odoo config — Add your Odoo URL, database, username, and API key to Hermes' config.yaml
3. Start Hermes — The Odoo tools are automatically available in every session

# Hermes config.yaml snippet
odoo:
  url: "https://your-instance.odoo4projects.com"
  db: "your-database"
  user: "agent@company.com"
  api_key: "your-api-key"
  readonly: true

When to use this

• Hermes Agent is your only tool and Odoo is your only backend
• You want the fastest possible setup
• Lowest latency — the agent talks directly to Odoo
• Full model access — the agent can work with any Odoo model your user has permissions for

Deep dive: Speed Run: Create an Odoo Community Agent from Zero

Method 2: MCP Server (Model Context Protocol)

The MCP approach inserts a translation layer between Hermes and Odoo. The mcp-server-odoo project (315+ GitHub stars, actively maintained) exposes Odoo models as MCP tools that Hermes can discover and call.

How it works: You run the MCP server locally on the same machine as Hermes. It listens on an HTTP port and translates MCP tool calls into Odoo XML-RPC requests. Hermes discovers the available tools automatically when you register the server.

Setup

1. Clone the server — git clone https://github.com/ivnvxd/mcp-server-odoo.git
2. Set environment variables — URL, database, username, API key
3. Start the server — uvx mcp-server-odoo (port 8000, streamable-http transport)
4. Register with Hermes — hermes mcp add odoo --url http://localhost:8000/mcp
5. Start Hermes — Odoo tools appear automatically

#!/usr/bin/env bash
export ODOO_URL="https://your-instance.odoo4projects.com"
export ODOO_DB="your-database"
export ODOO_USER="agent@company.com"
export ODOO_API_KEY="your-api-key"
export ODOO_READONLY=1
export ODOO_MCP_TRANSPORT=streamable-http
export ODOO_MCP_PORT=8000
export ODOO_YOLO=read

uvx mcp-server-odoo

When to use this

• Your agent connects to multiple tools (Odoo + GitHub + Slack + Notion)
• You want a standardized protocol for all tool connections
• You're already using MCP with other tools and want consistency
• You need to connect Hermes to Odoo without modifying Hermes configuration

Deep dive: Speed Run: Connect Hermes Agent to Odoo via MCP

Method 3: Custom Hermes Skill

The most flexible approach. You write a custom Hermes skill — a SKILL.md file — that defines exactly how the agent communicates with Odoo. This gives you full control over the tools, prompts, and error handling.

How it works: Hermes skills are markdown files with YAML frontmatter and a structured body. Your Odoo skill defines tools like search_leads, create_invoice, or check_inventory. Each tool uses terminal() to make curl calls to the Odoo XML-RPC endpoint, and the agent calls these tools by name during the conversation.

Setup

1. Create SKILL.md — in ~/.hermes/skills/odoo/SKILL.md
2. Define tools — Each tool has a name, description, parameter schema, and command template
3. Load the skill — Add it to your Hermes profile or load it in a session

# Odoo Hermes Skill

## Tools

### search_leads
Search CRM leads with filters.
Parameters: domain (list), limit (int, optional)
Command: `curl -s "$ODOO_URL" -d '{"params": {"model": "crm.lead", "method": "search_read", "args": [{{domain}}], "kwargs": {"limit": {{limit|5}}}}}'`

### create_lead
Create a new CRM lead.
Parameters: name (string), email (string, optional), phone (string, optional)
Command: `curl -s "$ODOO_URL" -d '{"params": {"model": "crm.lead", "method": "create", "args": [{"name": "{{name}}", "email_from": "{{email}}", "phone": "{{phone}}"}]}}'`

When to use this

• You need custom validation or business logic before/after Odoo calls
• You want specific tool names and descriptions tailored to your workflow
• You're building a specialized agent (e.g., "Odoo sales assistant")
• You want to combine Odoo calls with processing steps (e.g., search → analyze → summarize)