Reopen a milestone back to 'planned'.
AI agents use ppm_milestone_reopen to create or update resources in Qod Ppm Odoo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Qod Ppm Odoo environment.
This tool changes a milestone's state from closed/completed back to planned, which is a reversible modification of project data. It does not delete data (not Destructive), does not involve financial transactions (not Financial), and does not execute arbitrary code or commands (not Execute). It falls squarely into Write category as a state-change operation.
From the tool's definition Tool name 'ppm_milestone_reopen' and description 'Reopen a milestone back to \'planned\'' indicate a state transition that modifies existing data (milestone status) reversibly.
Attacks that exploit this kind of access
Reopen a milestone back to 'planned'. It is categorised as a Write tool in the Qod Ppm Odoo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Qod Ppm Odoo MCP server in PolicyLayer and add a rule for ppm_milestone_reopen: 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 Qod Ppm Odoo. Nothing to install.
ppm_milestone_reopen 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 ppm_milestone_reopen 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 ppm_milestone_reopen. 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.
ppm_milestone_reopen is provided by the Qod Ppm Odoo MCP server (wethti/qod-ppm-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 →