Get tools from all servers
AI agents call get_server_and_tools to retrieve information from MCP Registry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about server configurations and available tools without modifying, executing, or deleting anything. It has no side effects and poses minimal risk—it is purely informational. The blast radius is minimal since it only surfaces metadata about the MCP ecosystem itself.
From the tool's definition Tool name 'get_server_and_tools' and description 'Get tools from all servers' indicate a retrieval/query operation with no side effects. Returns metadata about available tools and servers.
Attacks that exploit this kind of access
Get tools from all servers. It is categorised as a Read tool in the MCP Registry MCP Server, which means it retrieves data without modifying state.
Register the MCP Registry MCP server in PolicyLayer and add a rule for get_server_and_tools: 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 MCP Registry. Nothing to install.
get_server_and_tools 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_server_and_tools 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_server_and_tools. 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_server_and_tools is provided by the MCP Registry MCP server (redmadrobot-rnd/mcp-registry). 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 →