AI agents use add-project to create or update resources in Things — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Things environment.
This tool creates new projects in the Things app, a reversible write operation. It does not delete data (not Destructive), execute arbitrary code (not Execute), or move money (not Financial). The severity is medium because miscreated projects are easily removable, but bulk creation could clutter the user's productivity system or be used to spam the app with unwanted entries.
From the tool's definition Tool name 'add-project' and server description states the tool 'integrate[s] with the Things productivity app to create, update, and manage todos and projects using its URL scheme.' The 'add' verb and presence of sibling tools 'add-todo', 'update', and…
Documented attack patterns abuse exactly the kind of access add-project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Things, and nothing reaches the server without passing your rules. This is the rule we recommend for add-project:
{
"version": "1",
"default": "deny",
"tools": {
"add-project": {
"limits": [
{
"counter": "add-project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add-project 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.
Free to start. No card required.
add-project. It is categorised as a Write tool in the Things MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Things 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 Things. 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 Things MCP server (jimfilippou/things-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Things, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Things tools catalogued and risk-classified — across an index of 43,000+ MCP servers.