Authoritative server read of a project — name, owning org, tier, effective status, active deploy, mailbox addresses, and usage vs. tier limits. Live API call; returns no keys (use project_keys for those).
AI agents call project_get to retrieve information from Run402 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation that retrieves project metadata and usage information. It explicitly does not return sensitive keys and has no capability to modify, delete, or execute operations. The blast radius of misuse is minimal—an attacker gains information about project configuration and resource consumption but cannot alter infrastructure or access credentials.
From the tool's definition Tool description explicitly states 'Authoritative server read of a project' and 'returns no keys (use project_keys for those)'. The function retrieves metadata (name, org, tier, status, deploy, mailbox, usage) with no side effects.
Attacks that exploit this kind of access
Authoritative server read of a project — name, owning org, tier, effective status, active deploy, mailbox addresses, and usage vs. tier limits. Live API call; returns no keys (use project_keys for those). It is categorised as a Read tool in the Run402 MCP Server, which means it retrieves data without modifying state.
Register the Run402 MCP server in PolicyLayer and add a rule for project_get: 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 Run402. Nothing to install.
project_get 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 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. 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 is provided by the Run402 MCP server (kychee-com/run402). 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 →