AI agents use odoo_mark_activity_done to create or update resources in Odooclaw — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Odooclaw environment.
This tool performs a reversible state modification (marking an activity as complete) rather than deletion or execution of arbitrary logic. It fits the Write category as it updates an activity record. Severity is medium because misuse could mark important business activities as done incorrectly, affecting workflow tracking, but the operation is reversible via updating the activity status again.
From the tool's definition Tool name 'odoo_mark_activity_done' indicates a state-change operation on an activity record in Odoo ERP. The 'mark' verb suggests updating an activity's status to 'done', which modifies data reversibly. Description is empty, limiting evidence strength.
Attacks that exploit this kind of access
odoo_mark_activity_done. It is categorised as a Write tool in the Odooclaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Odooclaw MCP server in PolicyLayer and add a rule for odoo_mark_activity_done: 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 Odooclaw. Nothing to install.
odoo_mark_activity_done 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_mark_activity_done 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_mark_activity_done. 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_mark_activity_done is provided by the Odooclaw MCP server (nicolasramos/odooclaw-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 →