AI agents use update-project to create or update resources in SupaThings MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SupaThings MCP environment.
The 'update-project' tool modifies existing project data reversibly within Things 3 (a task management application). This is a Write operation—data is changed but not destroyed and can be undone through subsequent updates. Severity is medium because misuse could corrupt task organization, but data remains recoverable and the blast radius is limited to one user's local task management system.
From the tool's definition Tool name is 'update-project' which indicates modification of project data. Server description states it 'enables AI agents to read and manage Things 3 data' and provides 'tools for project structural analysis and task placement', contextualizing this as a…
Documented attack patterns abuse exactly the kind of access update-project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SupaThings MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for update-project:
{
"version": "1",
"default": "deny",
"tools": {
"update-project": {
"limits": [
{
"counter": "update-project_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-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.
update-project. It is categorised as a Write tool in the SupaThings MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SupaThings MCP server in PolicyLayer and add a rule for update-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 SupaThings MCP. Nothing to install.
update-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 update-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 update-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.
update-project is provided by the SupaThings MCP server (soycanopa/supathings-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SupaThings MCP, 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.
37 SupaThings MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.