AI agents call rh11_projects_get to retrieve information from Rhodium11 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project information (schedule, services, SERP data) without creating, modifying, deleting, or executing any actions. It is a straightforward read operation on existing project data. Low severity reflects minimal blast radius—an agent misusing this tool could only access information already accessible to the authenticated user.
From the tool's definition Tool name 'rh11_projects_get' and description 'Get detailed info for a specific Rhodium11 project including schedule, services, and SERP data' indicate a retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
Get detailed info for a specific Rhodium11 project including schedule, services, and SERP data. It is categorised as a Read tool in the Rhodium11 MCP Server, which means it retrieves data without modifying state.
Register the Rhodium11 MCP server in PolicyLayer and add a rule for rh11_projects_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 Rhodium11. Nothing to install.
rh11_projects_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 rh11_projects_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 rh11_projects_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.
rh11_projects_get is provided by the Rhodium11 MCP server (rhodium11/rhodium11-mcp). 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 →