AI agents use set_project_path to create or update resources in Code Index — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Code Index environment.
This tool modifies the server's internal configuration by setting a project path parameter. While reversible (can be changed again), it affects subsequent indexing operations and alters the system state. It is Write rather than Execute because it configures parameters rather than triggering code execution.
From the tool's definition Tool name 'set_project_path' and description 'Set the base project path for indexing' indicate modification of configuration/settings state that controls the server's indexing behavior.
Documented attack patterns abuse exactly the kind of access set_project_path gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Index, and nothing reaches the server without passing your rules. This is the rule we recommend for set_project_path:
{
"version": "1",
"default": "deny",
"tools": {
"set_project_path": {
"limits": [
{
"counter": "set_project_path_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_project_path 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 the base project path for indexing. It is categorised as a Write tool in the Code Index MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Code Index MCP server in PolicyLayer and add a rule for set_project_path: 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 Index. Nothing to install.
set_project_path 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_path 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_path. 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_path is provided by the Code Index MCP server (johnhuang316/code-index-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Index, 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.
14 Code Index tools catalogued and risk-classified — across an index of 43,000+ MCP servers.