Retrieve canonical xgr-multi-bundle@1 Markdown documentation.
AI agents call get_xgr_multibundle_reference to retrieve information from XGR MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static documentation (Markdown reference material) about the xgr-multi-bundle specification. It has no ability to modify, delete, or execute operations on the blockchain or any system. The blast radius of misuse is minimal—an agent cannot cause financial, destructive, or operational harm by retrieving documentation.
From the tool's definition Tool name contains 'get_' and description states 'Retrieve canonical...Markdown documentation' — a read-only query operation with no side effects.
Attacks that exploit this kind of access
Retrieve canonical xgr-multi-bundle@1 Markdown documentation. It is categorised as a Read tool in the XGR MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the XGR MCP Gateway MCP server in PolicyLayer and add a rule for get_xgr_multibundle_reference: 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 XGR MCP Gateway. Nothing to install.
get_xgr_multibundle_reference is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_xgr_multibundle_reference 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 get_xgr_multibundle_reference. 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.
get_xgr_multibundle_reference is provided by the XGR MCP Gateway MCP server (xgr-network/xgr-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 →