Run a COQL SELECT query against Zoho CRM.
AI agents invoke coql_query to trigger actions in Zoho CRM MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
While the description mentions only SELECT queries, the tool executes arbitrary COQL (CRM Object Query Language) statements against Zoho CRM. Even read-only queries can expose sensitive CRM data at scale, and the ability to run arbitrary query strings means an agent could potentially extract bulk sensitive data. The Execute category applies because it runs dynamic queries whose effects depend on arguments.
From the tool's definition 'Run a COQL SELECT query against Zoho CRM' — executes arbitrary query language statements against the CRM database
Attacks that exploit this kind of access
Run a COQL SELECT query against Zoho CRM. It is categorised as a Execute tool in the Zoho CRM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Zoho CRM MCP Server MCP server in PolicyLayer and add a rule for coql_query: 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 Zoho CRM MCP Server. Nothing to install.
coql_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the coql_query 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 coql_query. 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.
coql_query is provided by the Zoho CRM MCP Server MCP server (lokimcpuniverse/zoho-crm-mcp-server). 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 →