Which Odoo versions are supported?

This server uses the JSON-RPC protocol, which is compatible with Odoo 14, 15, 16, 17, and 18. Both Odoo Community and Enterprise editions are supported.

Does it work with Odoo.com (SaaS)?

Yes! Works with both Odoo.com hosted instances and self-hosted Odoo servers. Just provide your instance URL and API key.

How do I generate an API Key?

Go to Settings → Users → select your user → API Keys tab → New API Key. Give it a descriptive name and copy the generated key.

Odoo Project MCP Server for CrewAI 7 tools — connect in under 2 minutes

Name: Odoo Project
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 7 Tools Framework

Connect your CrewAI agents to Odoo Project through the Vinkius — pass the Edge URL in the `mcps` parameter and every Odoo Project tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Odoo Project Specialist",
    goal="Help users interact with Odoo Project effectively",
    backstory=(
        "You are an expert at leveraging Odoo Project tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Odoo Project "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 7 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Odoo Project MCP Server

Connect Odoo ERP to any AI agent — manage your entire business without switching tabs.

When paired with CrewAI, Odoo Project becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Odoo Project tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

CRM — Search and create leads, track opportunities through your pipeline
Contacts — Find individual contacts and companies, create new partners
Sales — List and manage sales orders with full order details
Notes — Add comments and notes to any record in your Odoo instance

The Odoo Project MCP Server exposes 7 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Odoo Project to CrewAI via MCP

Follow these steps to integrate the Odoo Project MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 7 tools from Odoo Project

Why Use CrewAI with the Odoo Project MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Odoo Project through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Odoo Project + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Odoo Project MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Odoo Project for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Odoo Project, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Odoo Project tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Odoo Project against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Odoo Project MCP Tools for CrewAI (7)

These 7 tools become available when you connect Odoo Project to CrewAI via MCP:

odoo_create_project

project record. The name is the project title. Optionally link it to an existing customer/partner using their res.partner ID. Use when the user wants to set up a new project for internal work, a client engagement, or a product initiative. Create a new project in Odoo, optionally linked to a customer or partner

odoo_create_task

task record in the specified project. Requires the project.project ID (use odoo_list_projects to find it). Optionally assign to a res.users ID and set a deadline in YYYY-MM-DD format. Use when the user wants to add a to-do item, delegate work, or plan project deliverables. Create a new task within an Odoo project, optionally assigning it to a user with a deadline

odoo_list_projects

project records showing all active projects. Returns project name, project manager, linked customer/partner, total task count, start date, and end date. Use when the user asks about ongoing projects, wants a project overview, or needs to find a project ID for task creation. List all projects in Odoo with responsible person, customer, task count, and date range

odoo_list_tasks

task records. Optionally filter by project ID to see tasks for a specific project, or omit to see tasks across all projects. Returns task name, project, assigned users, kanban stage (e.g., New/In Progress/Done), priority (0=normal, 1=important), progress percentage, deadline, and creation date. Use when the user asks about to-do lists, task assignments, project progress, or upcoming deadlines. List project tasks in Odoo with assignee, kanban stage, priority, progress, and deadlines

odoo_list_timesheets

analytic.line records where project_id is set — these are timesheet entries that track hours worked. Returns description, project, task, employee, hours logged (unit_amount), and date. Use when the user asks about time tracking, billable hours, employee workload, or project time allocation. List timesheet entries in Odoo showing employee, project, task, hours logged, and date

odoo_log_timesheet

analytic.line record linking hours to a specific project and task. Requires project.project ID, project.task ID, hours worked, and a description of the work performed. Optionally specify a date (defaults to today). Use when the user wants to log time spent, track billable hours, or record daily work activities. Log a timesheet entry — record hours worked on a specific project task with a description

odoo_update_task

task record. You can change the task name, priority (0=normal, 1=important/starred), deadline (YYYY-MM-DD), or any other writable field. Use when the user wants to rename a task, change its priority, reschedule the deadline, or modify task details. Update an existing task in Odoo — change name, priority, deadline, or other properties

Example Prompts for Odoo Project in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Odoo Project immediately.

"Search for leads from the website"

"Show recent sales orders"

Troubleshooting Odoo Project MCP Server with CrewAI

Common issues when connecting Odoo Project to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Odoo Project + CrewAI FAQ

Common questions about integrating Odoo Project MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.