Show full config + cached capabilities for one target (credential masked).
AI agents call gateway_describe to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays configuration information and cached capabilities for inspection purposes. It has no side effects—it neither modifies data, executes operations, nor deletes anything. The masking of credentials demonstrates defensive design.
From the tool's definition Tool name 'gateway_describe' combined with description 'Show full config + cached capabilities for one target (credential masked)' indicates data retrieval only. The explicit note that credentials are masked confirms no sensitive data exposure.
Attacks that exploit this kind of access
Show full config + cached capabilities for one target (credential masked). It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for gateway_describe: 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 Claude Team MCP. Nothing to install.
gateway_describe 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 gateway_describe 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 gateway_describe. 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.
gateway_describe is provided by the Claude Team MCP server (lakshan12367/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 →