Show currently active tools after canonical + overlap filtering.
AI agents call catalog_active_tools to retrieve information from tin-canMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays the state of active tools within the catalog system. It retrieves information about which tools are currently available after filtering, comparable to a 'list' or 'get' operation. There are no modifications to data, no code execution, no destructive actions, and no financial implications.
From the tool's definition Tool name 'catalog_active_tools' and description 'Show currently active tools' indicates retrieval of status information with no side effects. The verb 'show' is a read-only operation.
Attacks that exploit this kind of access
Show currently active tools after canonical + overlap filtering. It is categorised as a Read tool in the tin-canMCP MCP Server, which means it retrieves data without modifying state.
Register the tin-can MCP server in PolicyLayer and add a rule for catalog_active_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 tin-canMCP. Nothing to install.
catalog_active_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 catalog_active_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 catalog_active_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.
catalog_active_tools is provided by the tin-can MCP server (juangrukat/tin-canmcp). 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 →