AI agents call lookup_pipelines to retrieve information from Kylas CRM without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the naming pattern and context from sibling tools (lookup_products, lookup_users, search_leads) strongly suggest this tool retrieves or lists pipeline data without modifying it. No side effects are implied. Confidence is moderate (0.7) due to lack of explicit documentation, but the semantic evidence from the tool name and server context supports a Read classification with low severity.
From the tool's definition Tool name 'lookup_pipelines' indicates a retrieval/query operation. The verb 'lookup' is consistent with Read-category tools like the sibling 'lookup_products' and 'lookup_users' on the same server.
Attacks that exploit this kind of access
lookup_pipelines. It is categorised as a Read tool in the Kylas CRM MCP Server, which means it retrieves data without modifying state.
Register the Kylas CRM MCP server in PolicyLayer and add a rule for lookup_pipelines: 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 Kylas CRM. Nothing to install.
lookup_pipelines 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 lookup_pipelines 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 lookup_pipelines. 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.
lookup_pipelines is provided by the Kylas CRM MCP server (akshaykylas94/MCP). 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 →