cronos_cerca
AI agents call cronos_cerca to retrieve information from Mcp Cronos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name indicates a search operation on the work diary system. Search operations retrieve data without modifying, deleting, or executing external operations, placing it in the Read category. Severity is low because searching a local work diary poses minimal risk even if misused by an agent—worst case is unauthorized information disclosure of personal work logs.
From the tool's definition Tool name 'cronos_cerca' suggests search functionality (Italian 'cerca' = 'search'). Server description mentions 'full-text search' as a capability. No description provided for the tool itself, limiting certainty.
Attacks that exploit this kind of access
cronos_cerca. It is categorised as a Read tool in the Mcp Cronos MCP Server, which means it retrieves data without modifying state.
Register the Mcp Cronos MCP server in PolicyLayer and add a rule for cronos_cerca: 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 Cronos. Nothing to install.
cronos_cerca 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 cronos_cerca 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 cronos_cerca. 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.
cronos_cerca is provided by the Mcp Cronos MCP server (mauriziomocci/mcp-cronos). 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 →