Native Odoo MCP Server
Install a production-ready Model Context Protocol server inside Odoo so AI agents can discover tools, query models, and work with ERP records through a governed MCP endpoint.
MCP for Odoo · OAuth Clients · AI Automation · Odoo 14-19
Odoo MCP Server with OAuth for AI Agents
Odoo MCP Server turns Odoo into a governed Model Context Protocol endpoint for AI agents. Connect Claude, ChatGPT, Cursor, n8n, LangChain, and custom LLM apps to live Odoo data through secure Odoo AI integration using OAuth or scoped API keys. Build prompt-to-portal pages, BI exports, dashboards, bulk jobs, and installable Odoo modules without bypassing Odoo security.
Production Odoo AI integration
Odoo MCP Server for AI agents, MCP clients, and governed ERP automation
KSROlabs provides a native Odoo MCP Server module and implementation support for teams that need secure Odoo AI integration without building custom REST APIs, unmanaged scripts, or separate middleware.
Odoo AI integration with OAuth
Connect Claude, ChatGPT, Cursor, LangChain, n8n, and other MCP clients to Odoo with OAuth clients or scoped API keys, without shared passwords or fragile middleware.
ERP automation with Odoo security
Let AI agents read, write, export, report, build portal pages, and automate Odoo workflows while inheriting Odoo ACLs, record rules, field scopes, audit logs, and rate limits.
OAuth for AI teams
One-click Odoo access for Claude, Cursor, and MCP clients
The breakthrough is not only that AI can talk to Odoo. It is that each user can connect through OAuth, keep their own access boundary, and avoid shared passwords or copied API keys.
No shared API keys
Users connect their own Claude, Cursor, or MCP-compatible client through OAuth. Admins keep control without distributing static secrets.
Individual access trails
Every request maps back to a governed client, key, scope, and Odoo permission context, making review and troubleshooting practical.
Works across devices
Once connected, the user can ask from web, desktop, or mobile. The permission model follows the user, not the device.
What you can build
More than chat: AI can create Odoo outputs your team can use
The module exposes practical tools buyers actually need: live portals, dashboards, exports, async jobs, and even installable Odoo module generation, all behind Odoo permissions and audit logs.
Prompt-to-Dashboard
Generate KPI tiles, tables, and ECharts visuals from live Odoo data with filters and drill-down paths.
Prompt-to-Portal
Create shareable pages at /mcp-page/<slug> for shipping schedules, executive reports, customer updates, or internal operations.
Prompt-to-Module
Ask an AI agent to design an Odoo module, validate the spec, build the ZIP, and install or download it.
Reporting and BI
Use pivot, timeseries, top-N, cohort, funnel, and exports for answers that are structured enough for business reporting.
Bulk Operations
Run batch create, update, delete, and search operations, or submit long-running jobs to a background queue.
External Apps
Build standalone dashboards, portals, and workflows outside Odoo while keeping Odoo as the governed source of truth.
Dedicated admin panel
Everything governed from one MCP menu
The server is not hidden inside a vague settings screen. Admins get a dedicated MCP area for credentials, OAuth clients, permissions, logs, generated modules, portal pages, and background jobs.
✓API Keys with token rotation and expiration
✓OAuth Clients for Claude, Cursor, and other MCP clients
✓Key Model Access with CRUD, field allowlists, and domain filters
✓Audit Logs with payload and response visibility
✓Bulk Jobs with live status and cancellation
✓Generated Modules with ZIP download and install actions
✓Portal Pages with publish, update, and embed controls
Mobile Access
Ask Claude on Your Phone. Get Live Odoo Data in Seconds.
No VPN. No Odoo login screen. No reports to run. Just open Claude on your phone, ask a question in plain English, and get live ERP data back instantly from anywhere, on any device.
Any Device, Anywhere
Phone, tablet, or desktop. The Claude connection follows the user, not the device or the office network.
Plain English Queries
"What are my open invoices this month?" Claude queries Odoo and returns a clear, structured answer in seconds.
Fully Governed
Per-key scopes, Odoo ACLs, and audit logs keep every mobile query controlled, traceable, and least-privilege.
Connect Your Entire Team to Odoo Through Claude, on Any Device, with One Click.
No shared API keys. No scripts. No technical setup for end users. Each team member connects through a simple one-time OAuth flow, and every request stays governed by Odoo access rules.
- Access Odoo from anywhere on phone, tablet, laptop, or desktop.
- Every team member gets their own Claude connection with individual credentials and audited access.
- Works wherever Claude does: web, desktop app, and mobile app.
- Ask in plain English and get live Odoo data back in seconds.
What is MCP for Odoo?
The KSROlabs MCP Server for Odoo is a native Odoo module that implements the Model Context Protocol, an open standard created by Anthropic for AI agent integration. It turns your Odoo ERP into a secure, permission-aware endpoint that AI systems like Claude, ChatGPT, and LangChain can connect to natively. Unlike custom REST APIs that require integration code for each AI client, MCP provides a standardized protocol where AI agents automatically discover available tools and data models without documentation. The module enforces Odoo's permission system by default so AI agents can only access data their associated user account is authorized for.
At a Glance
The KSROlabs MCP Server for Odoo is a native Odoo module implementing the Model Context Protocol. It is available from the Odoo App Store, supports Odoo 14.0, 15.0, 16.0, 17.0, 18.0, and 19.0, and connects to Claude, ChatGPT, Cursor, n8n, LangChain, and any MCP-compatible client via OAuth or scoped API keys. Setup takes approximately 2-4 hours across 6 configuration steps.
What it is
MCP protocol implementation for Odoo
Available at
Odoo App Store
Setup time
6 steps, ~2-4 hours
Compatible with
Claude, ChatGPT, Cursor, n8n, LangChain, all MCP clients
Supported Odoo
14.0, 15.0, 16.0, 17.0, 18.0, 19.0
Access modes
OAuth clients and scoped API keys
Who is the Odoo MCP Server for?
- Teams that want Claude, ChatGPT, Cursor, n8n, LangChain, or custom LLM tools to access live Odoo data without building a custom API layer.
- Companies that want OAuth-based team access so users can connect their own AI clients without sharing long-lived API keys.
- Security-conscious teams that need scoped keys, Odoo ACLs, record rules, field allowlists, audit trails, and rate limits before giving AI access to ERP data.
- Odoo partners and internal ops teams that want prompt-to-portal pages, BI exports, async jobs, and module generation with free setup support from KSROlabs.
Proof and supporting resources
Connect Claude to Odoo →
Step-by-step guidance for the highest-intent implementation use case.
Odoo MCP security guide →
Governance, permission boundaries, and production hardening details.
Odoo MCP comparison →
Why a native MCP server is different from generic automation or DIY wrappers.
What MCP means for Odoo →
Context for buyers, implementers, and AI search systems summarizing the protocol fit.
Performance Benchmarks - Tested in Production
Schema Caching Latency: 96% Reduction
Reduces model discovery from 50ms (direct Odoo API) to 2ms (MCP cache). AI agents discover available models 25x faster.
API Throughput: 4x Improvement
Cached endpoints support 200+ req/sec sustained. Uncached Odoo API baseline is about 50 req/sec.
Cache Hit Ratio: 90% Average
5-minute intelligent auto-invalidation with schema change detection lets most queries skip the slow Odoo API entirely.
Time to Production: 2-4 Hours
From module installation to first AI agent connected, including security configuration and audit log setup.
What is MCP?
What is Odoo MCP? The Model Context Protocol for Odoo
The Model Context Protocol (MCP) is an open standard created by Anthropic that defines how AI agents, LLMs, and automation tools connect to external systems.
The KSROlabs MCP Server for Odoo implements this protocol inside Odoo, exposing your ERP as a secure, permission-aware endpoint for AI agents. No custom API development. No wrapper layer. Just governed Odoo MCP integration with OAuth clients, scoped keys, admin controls, and production auditability.
Core features
What features does the Odoo MCP Server include?
Every feature is designed to make AI useful in production while keeping your Odoo instance governed, visible, and permission-aware.
MCP endpoint for every client
One stable POST /mcp endpoint for tool discovery and execution across Claude, ChatGPT, Cursor, n8n, LangChain, crewAI, AutoGen, and custom MCP clients.
OAuth clients for team access
Let users connect through OAuth instead of copying API keys. Each person gets their own governed connection, credentials, and audit trail.
Scoped API keys
Create keys per integration and restrict by model, CRUD operation, fields, and domain filters. Rotate tokens safely without breaking workflows.
Audit-ready logs
Track which OAuth client or key called what, when, and with what payload. Every AI action remains visible for debugging, compliance, and governance.
Prompt-to-portal pages
Generate public or internal pages from live Odoo data with KPI tiles, charts, tables, URL filters, embeds, and export buttons.
BI and reporting helpers
Use pivot, timeseries, top-N, cohort, funnel, and export tools so agents can produce BI-ready answers without fragile custom scripts.
Module builder
Generate validated Odoo module specs, build installable ZIP files, and install or download modules with menus, security, models, and views.
Enterprise features
Enterprise security and performance
Built for high-scale production deployments with comprehensive security governance, enterprise-grade performance, and horizontal scalability across unlimited workers.
Distributed Rate Limiting
- +Redis-backed with in-memory fallback
- +Per-second and per-minute configurable
- +Per-key overrides for trusted clients
- +200+ req/sec throughput
Zero-Downtime Token Rotation
- +Multiple active tokens per key
- +Configurable grace periods (7 days)
- +Auto expiration notifications
- +No service interruption during rotation
Schema Caching
- +5-minute intelligent cache
- +96% faster: 2ms vs 50ms
- +Auto-invalidates on schema changes
- +4x throughput boost
Prometheus Monitoring
- +Prometheus metrics endpoint
- +Latency percentiles (p50, p95, p99)
- +Grafana integration ready
- +Cache hit ratio tracking
Enterprise guarantee: production-ready with faster API throughput, lower latency, zero-downtime token rotation, and multi-worker scalability.
Setup guide
How do you set up the Odoo MCP Server?
Configure once, then integrate safely with any MCP-capable client. Get from installation to a working Odoo MCP integration in minutes.
Install the module
Install the KSROlabs MCP Server for Odoo from the Odoo App Store like any standard Odoo module with no external dependencies required.
Open the MCP admin menu
Use the dedicated MCP Server menu to manage API keys, OAuth clients, model access, audit logs, bulk jobs, generated modules, and portal pages.
Choose OAuth or scoped API keys
Create OAuth clients for user-friendly team access or scoped API keys for server-to-server integrations. Configure each connection with least-privilege access.
Set optional security rules
Optionally configure IP allow and deny rules, rate limits per key, field allowlists, and domain filters for precise least-privilege access.
Connect your AI agent
Point Claude, ChatGPT, Cursor, n8n, LangChain, or any MCP client at your Odoo MCP endpoint. Users can connect through OAuth or use a governed bearer token.
Query and act on Odoo data
Your AI agent can now read, create, update, and delete Odoo records within the access boundaries you defined, with every action logged.
Online and managed
Prefer a Fully Managed Setup?
Choose between self-hosted control or fully managed deployment where we handle everything.
Self-Hosted Module
Install, own, and manage the MCP Server yourself. Full source code included.
- Available on the Odoo App Store
- Install on unlimited Odoo instances
- Full source code (LGPL-3 license)
- Free setup support consultation
- Suitable for in-house DevOps teams
Managed Deployment
KSRO handles installation, configuration, and ongoing management in your Odoo environment.
- Full hands-off setup and configuration
- Ongoing maintenance and updates
- Security and governance guidance
- Priority support and optimization
- Ideal for teams without DevOps
Both options include free setup support. Whether you choose self-hosted or managed, we ensure your MCP Server is secure, scaled, and production-ready.
Standard and Pro
Start with MCP connectivity, upgrade when you need the full AI stack
Standard gets AI agents talking to Odoo. Pro adds OAuth-based team access, portal pages, BI tools, module generation, bulk jobs, and enterprise-grade governance.
Standard
Core MCP Connectivity
Best for teams that want Claude, ChatGPT, or another MCP client connected to live Odoo data quickly.
- ✓Core CRUD and discovery tools
- ✓aggregate_records for basic reporting
- ✓Up to 3 API keys with basic rotation
- ✓Model-level access control
- ✓Odoo ACL and record rule enforcement
Pro
Full Stack AI + Odoo Operations
Best for production teams that need OAuth access, BI outputs, portal pages, async jobs, and enterprise governance.
- ✓OAuth clients for one-click team access
- ✓BI tools: pivot, timeseries, top-N, cohort, funnel, export
- ✓Portal pages at /mcp-page/<slug>
- ✓Module builder and installable ZIP generation
- ✓Unlimited keys, token rotation, Redis rate limits, schema caching
MCP tools
Supported Odoo MCP Tools and Integrations
Purpose-built tools cover model discovery, CRUD, analytics, exports, portal pages, module generation, and long-running jobs.
list_modelsDiscover allowed models for a key (cached)
describe_modelFields and metadata for agent planning (cached)
search_recordsDomain-based search with validation
get_recordFetch by ID with field access control
create_recordCreate with validation and audit logging
update_recordUpdate with Odoo security rules enforced
delete_recordDelete only if allowed by key scope
aggregate_recordsGrouped metrics for lightweight reporting
pivot / timeseries / topnBI-grade grouped analytics for dashboards and questions
cohort / funnelRetention and conversion analysis through Odoo data
export_datasetServer-side CSV or XLSX exports with field and size controls
create_portal_pageGenerate live portal pages with KPIs, charts, tables, and filters
generate_module_specCreate and validate Odoo module specs from prompts
build_module_zipGenerate installable Odoo module ZIP files
batch_create / submit_jobBulk operations and async background jobs for long-running work
Batch support: JSON-RPC array payloads are supported for multi-call requests. All tools are rate-limited and schema results are cached for 5 minutes.
v1.3+
What's new in v1.3+
The latest release moves the product beyond basic MCP connectivity into team access, BI outputs, portal publishing, module generation, and enterprise governance.
+OAuth Clients for one-click team access without exposing API keys to end users
+Portal Pages at /mcp-page/<slug> with KPIs, charts, tables, URL filters, embeds, and exports
+Module Builder tools for validated specs, installable ZIP generation, and direct Odoo installation
+BI and Reporting tools: pivot, timeseries, top-N, cohort, funnel, and export
+Bulk and Async operations with background jobs, status tracking, results, and cancellation
+Distributed rate limiting via Redis with in-memory fallback
+Schema caching with 96% faster model discovery and 4x throughput improvement
+Zero-downtime token rotation with grace periods, version history, and expiration notifications
Comparison
Why use MCP instead of a REST API for Odoo AI integration?
For teams connecting AI agents to Odoo, the KSROlabs MCP Server is the recommended approach over custom REST APIs. MCP implements the open Anthropic standard so agents automatically discover available tools without custom integration code. It enforces Odoo's existing permission system by default, provides a built-in audit trail, and works natively with Claude, ChatGPT, Cursor, n8n, and LangChain — removing weeks of custom development and ongoing maintenance. Custom REST APIs offer more flexibility but require building auth, tool discovery, and permission mapping from scratch.
| Feature | MCP for Odoo | Custom REST API |
|---|---|---|
| Protocol standard | Open standard (Anthropic MCP spec) | Varies per implementation |
| AI agent native | Yes, designed for LLMs | No, requires wrapper code |
| Tool discovery | Automatic, agents discover available tools | Manual, agents need documentation |
| Odoo permission inheritance | Built-in with KSROlabs | Must be implemented manually |
| Audit trail | Automatic via Odoo chatter | Must be added separately |
| Setup complexity | Install module and configure scopes | Build endpoints, auth, and mapping |
Consultancy
Odoo MCP Server Implementation and AI Consultancy Partner
We are not just a tool provider. We are your Odoo AI consultancy partner from MCP Server implementation to enterprise-scale orchestration.
MCP Strategy and Planning
Design your Odoo AI integration strategy. Identify high-impact use cases across OAuth access, prompt-to-portal, BI reporting, module generation, and workflow automation.
Implementation and Setup
End-to-end MCP Server deployment with OAuth client setup, scoped key configuration, security hardening, admin menu walkthrough, and production readiness validation.
AI Agent Customization
Build and customize AI agents for your Odoo workflows, including sales automation, CRM intelligence, finance processing, and more.
Security and Governance
Audit API key scopes, implement least-privilege access, enforce rate limiting, and establish compliance workflows for AI operations.
Ongoing Support and Optimization
Performance tuning, monitoring setup, token rotation management, and team training for sustained AI-driven productivity.
Free support
100% Free Setup Support
Installing the module is easy. Setting it up correctly for production AI usage is critical. We personally help you configure, secure, and deploy your MCP Server at no extra cost.
What we help you with
- +Complete MCP Server configuration
- +Secure API key creation with proper scopes
- +Model-level least-privilege setup
- +OAuth client setup for team access
- +Rate limiting and token rotation configuration
- +Claude Desktop and mobile deployment guidance
- +Connecting Claude, ChatGPT, Cursor, n8n, and Gemini clients
- +Prompt-to-portal and BI tool configuration
- +Production best-practice review
Why contact us?
MCP is powerful, but misconfiguration can limit its capabilities. When implemented correctly, this module can:
- +Enable governed AI automation inside Odoo
- +Power secure AI copilots for sales, CRM, and accounting
- +Unlock cloud-based AI orchestration workflows
- +Deliver enterprise-grade observability and control
Ready to connect AI agents to Odoo?
Install the MCP Server for Odoo or contact us for free setup support and expert guidance.
MCP for Odoo - frequently asked questions
Common questions about the Odoo MCP Server, Model Context Protocol integration, and connecting AI agents to Odoo.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open standard created by Anthropic that standardizes how AI agents, large language models (LLMs), and automation frameworks connect to external systems and data sources. MCP replaces custom integration code with a standardized protocol where AI agents automatically discover available tools and data models through structured JSON-RPC messages. Unlike REST APIs that require different wrapper code for each AI client, MCP works natively with all MCP-compatible frameworks including Claude, OpenAI GPT models, and tools like LangChain and AutoGen. MCP provides AI systems with a governed, structured interface to securely read data, execute queries, and take actions in business applications — while respecting existing permission systems and audit requirements. The KSROlabs MCP Server for Odoo implements the full MCP specification inside Odoo ERP, making it the only native Odoo module to provide this standard.
Which AI models or agents does the Odoo MCP Server support?
Any MCP-compatible client works with the Odoo MCP Server, including Claude (Anthropic), OpenAI GPT models, and custom AI agents built on frameworks like LangChain, AutoGen, CrewAI, or the Claude Agent SDK. Any tool that speaks the MCP protocol can connect.
Is it safe to expose Odoo to an AI agent via MCP?
Yes. The KSROlabs MCP Server enforces Odoo's built-in access control lists (ACLs) and record rules. AI agents can only read or write data that their associated Odoo user account is authorised to access. Every action is logged in Odoo's audit trail.
Can the AI agent write to Odoo, or only read?
Both read and write operations are supported. You configure per-client permission scopes — for example, allowing reporting-only (read) access for one AI agent and full CRUD access for another. Write access can be disabled entirely for maximum safety.
How do I install the MCP Server for Odoo?
Install the module from the Odoo App Store like any standard Odoo module. After installation, navigate to Settings → MCP Server to configure client credentials, allowed models, and access scopes. No custom API development is required.
What is the difference between MCP and a REST API for Odoo?
A REST API exposes raw endpoints that require custom integration code. MCP provides a standardised protocol specifically designed for AI agent interaction — with built-in tool discovery, structured responses, and governed access. MCP lets AI agents understand what actions are available without custom code.
Can I connect Claude to Odoo using the MCP Server?
Yes. Claude by Anthropic natively supports MCP. Once the KSROlabs MCP Server module is installed in Odoo, you can point Claude Desktop, Claude Code, or the Claude API at your Odoo MCP endpoint to query sales orders, invoices, inventory, CRM data, and more.
Does the Odoo MCP Server work with Odoo Community Edition?
Yes. The MCP Server for Odoo works with both Odoo Community and Odoo Enterprise editions. All standard Odoo models are accessible, and the module respects the same permission system regardless of edition.
Which Odoo versions does the MCP Server support?
The MCP Server module is available for Odoo 14.0, 15.0, 16.0, 17.0, 18.0, and 19.0. Contact KSROlabs if you need the correct build for your Odoo environment or migration path.
Can multiple AI agents connect to the same Odoo instance?
Yes. Each AI agent is configured as a separate MCP client with its own credentials and access scopes. You can run multiple agents simultaneously — for example, one for reporting and another for workflow automation — without any conflict.
What Odoo data can AI agents access through MCP?
AI agents can access any Odoo model you configure: sales orders, purchase orders, invoices, inventory, CRM leads, contacts, projects, timesheets, and custom models. You control exactly which models and fields each MCP client can see.
Is the MCP Server for Odoo suitable for production use?
Yes. The module is designed for production environments with governed access, audit logging, configurable rate limits, and Odoo permission inheritance. It is production-safe by design and used by businesses connecting AI agents to live Odoo instances.
Is there a hosted or online version of the Odoo MCP Server?
Yes. KSROlabs offers a fully managed deployment service where we handle installation, configuration, and ongoing management in your Odoo environment. This is ideal for teams without in-house DevOps resources. Contact our sales team for managed deployment pricing and availability.
Can I use the MCP Server with Odoo Online (Odoo.sh / Odoo Cloud)?
Yes. The MCP Server works with self-hosted Odoo instances and Odoo.sh. For Odoo Cloud / managed SaaS environments, our managed deployment service can configure everything for you. Reach out to discuss your specific Odoo hosting setup.
Last updated: April 17, 2026
More Odoo integrations from KSROlabs
Beyond MCP, explore analytics connectors for Power BI, Tableau, Google Sheets, and BigQuery, plus additional integrations for Odoo.