Fetch UGF
AI agents call ugf_get_registry to retrieve information from Universal Gas Framework MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves registry data with no modification or side effects. The incomplete description 'Fetch UGF' suggests a simple data retrieval operation. Given the server's purpose, a registry fetch would provide configuration or reference data needed for cross-chain transactions.
From the tool's definition Tool name and description indicate a fetch operation ('Fetch UGF' is incomplete but suggests retrieval; 'get_registry' implies querying a registry).
Attacks that exploit this kind of access
Fetch UGF. It is categorised as a Read tool in the Universal Gas Framework MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Universal Gas Framework MCP Server MCP server in PolicyLayer and add a rule for ugf_get_registry: 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 Universal Gas Framework MCP Server. Nothing to install.
ugf_get_registry 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 ugf_get_registry 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 ugf_get_registry. 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.
ugf_get_registry is provided by the Universal Gas Framework MCP Server MCP server (tychiwallet/ugf-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 →