Get metadata for all registered MCP tools.
AI agents call get_tool_catalog to retrieve information from Mcp Stargazing 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 to enumerate metadata about registered tools. It has no side effects, cannot execute operations, and cannot modify or delete data. The blast radius of misuse is minimal—an AI agent could only learn what tools exist, which is informational. This is a classic Read category operation.
From the tool's definition Tool name 'get_tool_catalog' combined with description 'Get metadata for all registered MCP tools' indicates a retrieval operation that queries and returns information about available tools without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Get metadata for all registered MCP tools. It is categorised as a Read tool in the Mcp Stargazing MCP Server, which means it retrieves data without modifying state.
Register the Mcp Stargazing MCP server in PolicyLayer and add a rule for get_tool_catalog: 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 Stargazing. Nothing to install.
get_tool_catalog 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_tool_catalog 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_tool_catalog. 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_tool_catalog is provided by the Mcp Stargazing MCP server (stargazer1995/mcp-stargazing). 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 →