Update existing records in an Odoo model.
AI agents use odoo_write to create or update resources in MCP Odoo Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Odoo Server environment.
The tool performs reversible modifications to existing data records through Odoo's CRUD interface. While it modifies business-critical data that could have significant downstream effects (justifying 'high' severity), it is not destructive (data is not deleted), not financial, and not code execution. It falls clearly into the Write category.
From the tool's definition Tool name is 'odoo_write' and description explicitly states 'Update existing records in an Odoo model.' This is a write operation that modifies data in the database.
Attacks that exploit this kind of access
Update existing records in an Odoo model. It is categorised as a Write tool in the MCP Odoo Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Odoo Server MCP server in PolicyLayer and add a rule for odoo_write: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Odoo Server. Nothing to install.
odoo_write is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the odoo_write rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for odoo_write. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
odoo_write is provided by the MCP Odoo Server MCP server (malvernbright/odoo-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →