AI agents use manage_projects 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.
Project management in ERP systems involves creating and modifying project data (Write category), but likely not irreversible deletion (not Destructive) or financial transactions (not Financial). The severity is high because misuse could affect project planning, resource allocation, and team coordination across an organization.
From the tool's definition Tool name is 'manage_projects' with description 'Project management and planning'. In the context of Odoo ERP systems, project management operations typically involve creating, updating, and modifying project records, timelines, assignments, and resource…
Attacks that exploit this kind of access
Project management and planning. 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 manage_projects: 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.
manage_projects 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 manage_projects 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 manage_projects. 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.
manage_projects 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 →