Fetch a contact by ID.
AI agents call zoho_desk_get_contact to retrieve information from Vibing Steampunk (vsp) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'Fetch' and the singular retrieval pattern ('by ID') indicate a Read operation. No data is created, modified, deleted, or executed. The contact information retrieved from a support/helpdesk system (Zoho Desk) has minimal blast radius for misuse — an AI could at worst access contact details already available in the system.
From the tool's definition Tool name 'zoho_desk_get_contact' with description 'Fetch a contact by ID' — this is a retrieval operation that queries data without modification or side effects.
Attacks that exploit this kind of access
Fetch a contact by ID. It is categorised as a Read tool in the Vibing Steampunk (vsp) MCP Server, which means it retrieves data without modifying state.
Register the Vibing Steampunk (vsp) MCP server in PolicyLayer and add a rule for zoho_desk_get_contact: 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 Vibing Steampunk (vsp). Nothing to install.
zoho_desk_get_contact 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 zoho_desk_get_contact 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 zoho_desk_get_contact. 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.
zoho_desk_get_contact is provided by the Vibing Steampunk (vsp) MCP server (sangvucitek/mcp_sap). 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 →