AI agents call get_project_overview to retrieve information from Pl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns project metadata and block status information. It performs no mutations, deletions, executions, or financial operations. It is a straightforward data retrieval operation with no side effects, fitting squarely in the Read category with low severity since it only exposes existing project state information.
From the tool's definition The tool description explicitly states it 'Get[s] project overview' and retrieves information about 'blocks and their statuses' (calculationStatus, canRun, stale, errors, upstreams/downstreams).
Attacks that exploit this kind of access
Get project overview with all blocks and their statuses (calculationStatus, canRun, stale, errors, upstreams/downstreams). It is categorised as a Read tool in the Pl MCP Server, which means it retrieves data without modifying state.
Register the Pl MCP server in PolicyLayer and add a rule for get_project_overview: 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 Pl. Nothing to install.
get_project_overview 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 get_project_overview 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 get_project_overview. 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.
get_project_overview is provided by the Pl MCP server (@milaboratories/pl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →