AI agents use jsr_accept_scope_invite to create or update resources in JSR MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your JSR MCP environment.
Accepting a scope invite modifies user permissions and scope membership, which is a reversible write operation. It does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial). While it has security implications if misused by an agent (could grant unintended scope access), the blast radius is localized to scope membership changes, warranting medium severity rather than high.
From the tool's definition Tool name 'jsr_accept_scope_invite' and description 'Accept an invite to a scope' indicate a state-changing action that modifies membership or permissions within a scope.
Attacks that exploit this kind of access
Accept an invite to a scope (requires authentication). It is categorised as a Write tool in the JSR MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the JSR MCP server in PolicyLayer and add a rule for jsr_accept_scope_invite: 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 JSR MCP. Nothing to install.
jsr_accept_scope_invite 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 jsr_accept_scope_invite 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 jsr_accept_scope_invite. 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.
jsr_accept_scope_invite is provided by the JSR MCP server (wyattjoh/jsr-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 →