Odoo MCP Server

Odoo MCP Server

An enterprise-grade MCP server for interacting with Odoo ERP through AI assistants, enabling guided workflows, native BI, and deep introspection.

Category
Visit Server

README

Odoo MCP Server — Agentic Edition

PyPI Python License: MIT ES

An enterprise-grade Model Context Protocol (MCP) server for interacting with Odoo ERP through AI assistants. Unlike a traditional database connector, this server is designed as an agentic bridge: it teaches the AI how to navigate Odoo, understand its business logic, and perform complex data analysis.


Why Agentic Edition?

  • Guided Workflows (Prompts) — Native instructions that teach your AI how to audit inventory, analyse sales, or review security permissions step by step, without writing prompts from scratch.
  • Native BI — Optimised support for read_group and advanced analytical operations, allowing the AI to generate financial reports or KPIs instantly.
  • Deep Introspection — Tools that grant the AI X-ray vision: discover available action buttons, inspect view XML architectures, evaluate security rules — reducing hallucinations to a minimum.
  • Zero extra dependencies — Uses only Python stdlib (urllib, json, csv, xml) plus the mcp package. No requests, no odoorpc.
  • Built-in Security — Uses Odoo's own XML-RPC layer; the MCP server cannot bypass permissions the user doesn't already have.

Installation

# Recommended — isolated and fast
uv tool install odoo-mcp-server-conn

# Standard
pip install odoo-mcp-server-conn

Configuration

Environment variables

Variable Required Description
ODOO_URL Your Odoo URL (e.g. http://localhost:8069)
ODOO_DB Database name
ODOO_USERNAME User login or email
ODOO_PASSWORD Password or API Key (strongly recommended)
MCP_AUTH_CACHE_TTL Seconds before re-authenticating (default: 300)

Tip: Always prefer an API Key over a plain password. Generate one in Odoo under Settings → Users → Your User → API Keys.


Claude Code (CLI)

Run this command once — it stores the configuration permanently for the current project:

claude mcp add odoo-server \
  --env ODOO_URL=http://localhost:8069 \
  --env ODOO_DB=my_database \
  --env ODOO_USERNAME=admin \
  --env ODOO_PASSWORD=my_api_key \
  -- odoo-mcp-server-conn

Verify the connection inside Claude Code:

/mcp

<details> <summary>Project-scoped config — share with your team via <code>.mcp.json</code></summary>

Add --scope project to create a .mcp.json at the repository root that your whole team can use. Each developer supplies their own credentials via environment variables or CI secrets.

claude mcp add odoo-server \
  --scope project \
  --env ODOO_URL=http://localhost:8069 \
  --env ODOO_DB=my_database \
  --env ODOO_USERNAME=admin \
  --env ODOO_PASSWORD=my_api_key \
  -- odoo-mcp-server-conn

</details>


Claude Desktop

Locate your config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following block:

{
  "mcpServers": {
    "odoo-server": {
      "command": "odoo-mcp-server-conn",
      "env": {
        "ODOO_URL": "http://localhost:8069",
        "ODOO_DB": "my_database",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "my_api_key"
      }
    }
  }
}

VS Code (Copilot / Cline / Roo Code)

Add to your .vscode/mcp.json (workspace-level) or user MCP settings:

{
  "servers": {
    "odoo-server": {
      "type": "stdio",
      "command": "odoo-mcp-server-conn",
      "env": {
        "ODOO_URL": "http://localhost:8069",
        "ODOO_DB": "my_database",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "my_api_key"
      }
    }
  }
}

<details> <summary>Cline / Roo Code — <code>cline_mcp_settings.json</code></summary>

{
  "mcpServers": {
    "odoo-server": {
      "command": "odoo-mcp-server-conn",
      "env": {
        "ODOO_URL": "http://localhost:8069",
        "ODOO_DB": "my_database",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "my_api_key"
      }
    }
  }
}

</details>


Cursor IDE

  1. Go to Settings → Features → MCP.
  2. Click Add new server → type command.
  3. Command: odoo-mcp-server-conn.
  4. Add each environment variable in the Env vars section.

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "odoo-server": {
      "command": "odoo-mcp-server-conn",
      "env": {
        "ODOO_URL": "http://localhost:8069",
        "ODOO_DB": "my_database",
        "ODOO_USERNAME": "admin",
        "ODOO_PASSWORD": "my_api_key"
      }
    }
  }
}

Tools

CRUD — Core operations

Tool Odoo method Description
search_records search Return IDs matching a domain filter
read_records read Read fields from records by ID
search_read_records search_read Search + read in one optimised call
create_record create Create a new record
update_record write Update existing records
delete_record unlink Delete records ⚠️
count_records search_count Count without loading records (fast)

Introspection — understand the data model in real time

Tool Description
get_model_fields Live schema of any model (types, relations, required flags)
get_view_architecture Final merged XML of a view (form / tree / kanban / search)
get_workflow_states States, stages, and transition buttons of a model
get_action_buttons All buttons in a view with visibility conditions and groups
get_related_records Auto-resolved Many2one / One2many / Many2many relations
get_security_rules ACL and ir.rule records for a model
explain_domain Translates an Odoo domain filter into plain English

BI & Analytics

Tool Description
read_group GROUP BY with sums, counts, averages. Supports :month / :year date grouping
export_to_csv Export records to a CSV string (up to 1 000 rows)
get_available_reports List PDF / HTML reports available for a model

Wildcard

Tool Description
execute_method Call any public Odoo method (e.g. action_confirm, button_validate)

Guided Prompts (pre-trained workflows)

Invoke these prompts directly from your AI client to start a structured analysis:

Prompt What it does
analyze_sales Sales KPIs — revenue trend, top customers, conversion rate
diagnose_inventory Low-stock products, stuck transfers, warehouse utilisation
audit_permissions Cross-reference security groups with ACL, flag over-privileged users
financial_overview Cash flow overview — AR, AP, invoicing by period

Resources (navigable URIs)

The AI can query these URIs directly as if browsing the ERP:

URI Description
odoo://models Master list of all models installed in the instance
odoo://fields/{model} Data dictionary for a specific model
odoo://record/{model}/{id} Complete record sheet
odoo://search/{model}/{domain} Instant search, e.g. odoo://search/res.partner/[["is_company","=",true]]

Security

  • The server operates entirely through Odoo's XML-RPC layer — it cannot bypass any permission the authenticated user doesn't already have in the ERP.
  • No raw SQL, no forced commits, no ORM bypass.
  • Credentials are read exclusively from environment variables — never hardcoded.

License: MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured