AI agents use invite_to_space to create or update resources in Repsona — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Repsona environment.
Inviting members to a space is a reversible operation that modifies the collaboration structure and access permissions. While it affects user access and could have security implications if misused, it is not destructive (invitations can be revoked), does not move money, and does not execute arbitrary code. It falls under Write as it creates new collaborative relationships and modifies space membership.
From the tool's definition Tool name 'invite_to_space' and description indicate it adds new members to a space, which creates new access relationships in the system. Description states 'Owner/Admin権限が必要' (Owner/Admin permissions required), confirming it modifies collaborative access.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
新しいメンバーをスペースに招待します(Owner/Admin権限が必要). It is categorised as a Write tool in the Repsona MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Repsona MCP server in PolicyLayer and add a rule for invite_to_space: 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 Repsona. Nothing to install.
invite_to_space 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 invite_to_space 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 invite_to_space. 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.
invite_to_space is provided by the Repsona MCP server (@bellx2/repsona-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 →