Return the current PROJECT_ROOT used by tools
AI agents call project_get_root to retrieve information from 8th Wall MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple getter that returns the current project root path. It retrieves information about the tool's operating context without performing any operations, modifying data, executing code, or causing side effects. The tool has a read-only nature with minimal security impact—knowing the project root is low risk compared to tools that create, execute, or delete resources.
From the tool's definition Tool name 'project_get_root' and description 'Return the current PROJECT_ROOT used by tools' indicate a retrieval of configuration/state information with no modification or execution capability.
Documented attack patterns abuse exactly the kind of access project_get_root gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and 8th Wall MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for project_get_root:
{
"version": "1",
"default": "deny",
"tools": {
"project_get_root": {}
}
}project_get_root is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return the current PROJECT_ROOT used by tools. It is categorised as a Read tool in the 8th Wall MCP Server MCP Server, which means it retrieves data without modifying state.
Register the 8th Wall MCP Server MCP server in PolicyLayer and add a rule for project_get_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 8th Wall MCP Server. Nothing to install.
project_get_root is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the project_get_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 project_get_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.
project_get_root is provided by the 8th Wall MCP Server MCP server (superdwayne/8thwallmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 8th Wall MCP Server, 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.
64 8th Wall MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.