Move a lead to a different pipeline stage.
AI agents use update_lead_stage to create or update resources in Outlet das Cores CRM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Outlet das Cores CRM environment.
This tool creates or modifies data reversibly—moving a lead between pipeline stages is an update operation that changes CRM state but does not delete data. The effect is material (affects business processes and pipeline tracking) and could impact sales workflows if misused by an AI agent (e.g., moving high-value leads to wrong stages), warranting 'high' severity.
From the tool's definition The tool name is 'update_lead_stage' and the description states it will 'Move a lead to a different pipeline stage.' This modifies the state of a lead record in the CRM system.
Attacks that exploit this kind of access
Move a lead to a different pipeline stage. It is categorised as a Write tool in the Outlet das Cores CRM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Outlet das Cores CRM MCP server in PolicyLayer and add a rule for update_lead_stage: 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 Outlet das Cores CRM. Nothing to install.
update_lead_stage is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_lead_stage 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 update_lead_stage. 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.
update_lead_stage is provided by the Outlet das Cores CRM MCP server (oeduardomanoel/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 →