todoist_projects

THE RISK

Medium Risk

Why todoist_projects needs a policy

The tool spans Read (query), Write (create, update), and potentially Destructive (archive) operations. However, archiving in Todoist is reversible (projects can be unarchived), so it qualifies as Write rather than Destructive. The primary concern is that an AI agent could create, modify, or reorganize projects without authorization.

From the tool's definition Tool description states it can 'create, read, update, archive, and query projects' — the write operations (create, update, archive) modify project state reversibly. Archiving is not truly destructive since projects can typically be restored in Todoist.

Documented attack patterns abuse exactly the kind of access todoist_projects gives an agent:

POLICY

How to control todoist_projects

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Todoist, and nothing reaches the server without passing your rules. This is the rule we recommend for todoist_projects:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "todoist_projects": {
      "limits": [
        {
          "counter": "todoist_projects_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

todoist_projects stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Mcp Todoist — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mcp Todoist tools

Destructive todoist_bulk_tasks Perform bulk operations on up to 50 Todoist tasks. Supports update, complete, uncomplete, Destructive todoist_comments Comment management for Todoist tasks and projects - create, read, update, delete comments Destructive todoist_labels label management for Todoist - create, read, update, delete labels with full CRUD operatio Destructive todoist_sections Section management within Todoist projects - create, read, update, delete, and reorder sec Destructive todoist_tasks Comprehensive task management for Todoist - create, read, update, delete, and query tasks Write todoist_reminders Manage reminders for Todoist tasks. Supports three reminder types: relative (minutes befor Read todoist_filters Filter management and task querying for Todoist - query existing filters, retrieve tasks w

All 8 Mcp Todoist tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about todoist_projects

What does the todoist_projects tool do? +

Complete project management for Todoist - create, read, update, archive, and query projects with metadata support. It is categorised as a Write tool in the Mcp Todoist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on todoist_projects? +

Register the Mcp Todoist MCP server in PolicyLayer and add a rule for todoist_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 Mcp Todoist. Nothing to install.

What risk level is todoist_projects? +

todoist_projects is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit todoist_projects? +

Yes. Add a rate_limit block to the todoist_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.

How do I block todoist_projects completely? +

Set action: deny in the PolicyLayer policy for todoist_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.

What MCP server provides todoist_projects? +

todoist_projects is provided by the Mcp Todoist MCP server (shayonpal/mcp-todoist). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Todoist tool call.

Start from Mcp Todoist, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →