Invite a user to collaborate on a board via email
AI agents use share_board_with_user to create or update resources in Miro MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Miro MCP Server environment.
share_board_with_user creates a new collaborator relationship on a board—a reversible modification of access control metadata. This is not destructive (the invitation can be revoked), not financial, not code execution. It is Write because it durably modifies board state by adding a new principal with collaborator privileges.
From the tool's definition Tool description states it 'Invite a user to collaborate on a board via email', which creates a new access/permission record.
Attacks that exploit this kind of access
Invite a user to collaborate on a board via email. It is categorised as a Write tool in the Miro MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Miro MCP Server MCP server in PolicyLayer and add a rule for share_board_with_user: 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 Miro MCP Server. Nothing to install.
share_board_with_user 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 share_board_with_user 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 share_board_with_user. 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.
share_board_with_user is provided by the Miro MCP Server MCP server (soul-script/miro-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 →