AI agents call get_contract_role to retrieve information from UluVoiMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query/lookup operation that retrieves existing contract metadata from the Voi blockchain semantic layer. It has no side effects, creates no resources, executes no code, and cannot delete or modify data. The tool simply translates raw blockchain data into human-readable contract role information, which is a classic Read operation.
From the tool's definition Tool name 'get_contract_role' and description 'Get the role and purpose of a specific contract' indicate data retrieval with no modification or execution. Returns informational metadata about contract roles (liquidity-pool, bridge, registry).
Attacks that exploit this kind of access
Get the role and purpose of a specific contract on Voi (e.g. liquidity-pool, bridge, registry). It is categorised as a Read tool in the UluVoiMCP MCP Server, which means it retrieves data without modifying state.
Register the UluVoi MCP server in PolicyLayer and add a rule for get_contract_role: 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 UluVoiMCP. Nothing to install.
get_contract_role 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_contract_role 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_contract_role. 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_contract_role is provided by the UluVoi MCP server (maidtoshelly/uluvoimcp). 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 →