AI agents use update_records to create or update resources in Odoo-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odoo-MCP environment.
This tool modifies existing data reversibly (records can be updated again or reverted), which fits the Write category. Severity is high because Odoo ERP systems manage critical business data (financials, inventory, HR, sales), and uncontrolled updates across 'any model' could cause widespread business disruption.
From the tool's definition Tool name 'update_records' combined with description 'Update existing records in any Odoo model' clearly indicates data modification capability. The scope 'any Odoo model' indicates broad access across the ERP system.
Attacks that exploit this kind of access
Update existing records in any Odoo model. It is categorised as a Write tool in the Odoo-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odoo- MCP server in PolicyLayer and add a rule for update_records: 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 Odoo-MCP. Nothing to install.
update_records 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 update_records 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 update_records. 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.
update_records is provided by the Odoo- MCP server (ridrisa/odoo-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 →