Search the full catalog by name/description; no activation required.
AI agents call catalog_search_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.
The tool performs a retrieval operation (searching) over catalog metadata. It does not create, modify, delete, execute, or move resources. The 'no activation required' clause reinforces that it is passive and informational only. This fits the Read category with low severity since it only accesses potentially public or authorized catalog information with no blast radius from misuse.
From the tool's definition Tool description explicitly states 'Search the full catalog by name/description; no activation required.' This is a query/search operation with no side effects.
Attacks that exploit this kind of access
Search the full catalog by name/description; no activation required. 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_search_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_search_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_search_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_search_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_search_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 →