AI agents use set_project_root to create or update resources in Code Mode Toon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Mode Toon environment.
This is a Write operation because it creates or modifies configuration data (the project root setting). It is reversible—the root can be changed again. Severity is medium because misconfiguration could cause subsequent operations to target wrong paths, but the tool itself doesn't directly access, delete, or execute code. Confidence is 0.7 due to the minimal description providing limited operational context.
From the tool's definition The tool name is 'set_project_root' and description states 'Set project root for path resolution.' This modifies configuration state (the project root setting) that affects how the system resolves paths going forward.
Risk signalsAdmin/system-level operation
Documented attack patterns abuse exactly the kind of access set_project_root gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Mode Toon, and nothing reaches the server without passing your rules. This is the rule we recommend for set_project_root:
{
"version": "1",
"default": "deny",
"tools": {
"set_project_root": {
"limits": [
{
"counter": "set_project_root_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_project_root 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.
Set project root for path resolution. It is categorised as a Write tool in the Code Mode Toon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code Mode Toon MCP server in PolicyLayer and add a rule for set_project_root: 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 Code Mode Toon. Nothing to install.
set_project_root 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 set_project_root 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 set_project_root. 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.
set_project_root is provided by the Code Mode Toon MCP server (ziad-hsn/code-mode-toon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Mode Toon, 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 Code Mode Toon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.