Trigger a specific salesbot for a lead or contact.
AI agents invoke run_salesbot to trigger actions in Kommo 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.
This tool executes an external operation (salesbot trigger) whose side effects are determined by the salesbot's configuration, not by direct parameters to this tool. It is Execute rather than Write because it invokes an autonomous agent/workflow whose behavior is opaque to the direct caller.
From the tool's definition Tool description states 'Trigger a specific salesbot for a lead or contact' — the verb 'trigger' indicates activation of an external operation (a salesbot, likely an automated workflow or bot).
Attacks that exploit this kind of access
Trigger a specific salesbot for a lead or contact. It is categorised as a Execute tool in the Kommo MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kommo MCP Server MCP server in PolicyLayer and add a rule for run_salesbot: 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 Kommo MCP Server. Nothing to install.
run_salesbot 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 run_salesbot 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 run_salesbot. 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.
run_salesbot is provided by the Kommo MCP Server MCP server (wdavidce/kommo-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 →