Set person_id on a deal (replaces any previously-linked contact). Auto-backed up.
AI agents use link_person_to_deal to create or update resources in Mcp Pipedrive — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Pipedrive environment.
This tool modifies deal data by linking a person to a deal, which is a reversible write operation. The phrase 'replaces any previously-linked contact' confirms it modifies existing state. While it changes data, it is not destructive (the change can be undone by linking a different person), not financial (no money moves), and not code execution.
From the tool's definition Set person_id on a deal (replaces any previously-linked contact). Auto-backed up.
Attacks that exploit this kind of access
Set person_id on a deal (replaces any previously-linked contact). Auto-backed up. It is categorised as a Write tool in the Mcp Pipedrive MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Pipedrive MCP server in PolicyLayer and add a rule for link_person_to_deal: 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 Mcp Pipedrive. Nothing to install.
link_person_to_deal 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 link_person_to_deal 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 link_person_to_deal. 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.
link_person_to_deal is provided by the Mcp Pipedrive MCP server (leonardoceron-yvy/yvy-mcp-pipedrive). 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 →