AI agents call list_wallets to retrieve information from Solblade without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves wallet metadata (labels, groups, tags) without creating, modifying, deleting, or executing any transactions. It is a pure read operation that poses minimal security risk, particularly within a scoped MCP wallet system with audit logging. The severity is low because listing wallet identifiers and metadata has limited blast radius unless combined with other operations.
From the tool's definition Tool name 'list_wallets' and description 'List all wallets with labels, groups, and tags' indicate a query/retrieval operation with no modification or execution of actions.
Attacks that exploit this kind of access
List all wallets with labels, groups, and tags. It is categorised as a Read tool in the Solblade MCP Server, which means it retrieves data without modifying state.
Register the Solblade MCP server in PolicyLayer and add a rule for list_wallets: 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 Solblade. Nothing to install.
list_wallets 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 list_wallets 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 list_wallets. 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.
list_wallets is provided by the Solblade MCP server (nullxnothing/solblade). 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 →