add_project
AI agents use add_project to create or update resources in Todoist MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todoist MCP Server environment.
Creating a project in Todoist is a Write operation—it creates new data that can be modified or deleted later. The effect is reversible and has minimal blast radius if invoked erroneously. No data destruction, code execution, or financial impact. Severity is low because project creation alone carries minimal risk compared to batch deletions or destructive operations.
From the tool's definition Tool name is 'add_project' on a task management server (Todoist MCP Server) that 'Enables task, project, section, label, and comment management.' The name 'add_project' indicates creation of a new project resource.
Attacks that exploit this kind of access
add_project. It is categorised as a Write tool in the Todoist MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todoist MCP Server MCP server in PolicyLayer and add a rule for add_project: 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 Todoist MCP Server. Nothing to install.
add_project 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 add_project 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 add_project. 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.
add_project is provided by the Todoist MCP Server MCP server (oauthbringer/todoist-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 →