AI agents use update-lead to create or update resources in Pipedrive MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pipedrive MCP Server environment.
Updating a lead modifies existing data but does not irreversibly destroy it (which would be Destructive) nor does it move money (Financial) or execute arbitrary code (Execute). Updates are reversible through subsequent corrections or version recovery in most CRM systems.
From the tool's definition Tool description explicitly states 'Update an existing lead in Pipedrive', which modifies data reversibly. The tool is part of a CRUD-enabled server providing 'full CRUD access to Pipedrive CRM API', confirming write capabilities.
Documented attack patterns abuse exactly the kind of access update-lead gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pipedrive MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for update-lead:
{
"version": "1",
"default": "deny",
"tools": {
"update-lead": {
"limits": [
{
"counter": "update-lead_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update-lead stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Update an existing lead in Pipedrive. It is categorised as a Write tool in the Pipedrive MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pipedrive MCP Server MCP server in PolicyLayer and add a rule for update-lead: 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 Pipedrive MCP Server. Nothing to install.
update-lead 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 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. 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 is provided by the Pipedrive MCP Server MCP server (teapot-agency/mcp_pipedrive). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pipedrive MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
39 Pipedrive MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.