AI agents call describe_tenant to retrieve information from Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name and sibling context indicate this tool queries or retrieves tenant information without modifying state. Multi-tenant documentation servers typically expose describe/get operations for metadata retrieval. No evidence of write, delete, execute, or financial operations. Severity is low because reading tenant metadata has minimal blast radius in a documentation indexing system.
From the tool's definition Tool name 'describe_tenant' suggests retrieval of tenant metadata; sibling tools 'find_tenant' and 'list_tenants' are clearly read-only operations, establishing a Read-oriented context. Description is empty, lowering confidence slightly.
Attacks that exploit this kind of access
describe_tenant. It is categorised as a Read tool in the Docs MCP Server, which means it retrieves data without modifying state.
Register the Docs MCP server in PolicyLayer and add a rule for describe_tenant: 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 Docs. Nothing to install.
describe_tenant 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 describe_tenant 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 describe_tenant. 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.
describe_tenant is provided by the Docs MCP server (pankaj28843/docs-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 →