CRITICAL SECURITY: Scan for dApps with spending rights on your wallet. Finds ALL token approvals/delegations (unlimited and limited) and rates them by risk. Risk Levels: - HIGH: Unknown dApps with unlimited approval — can drain your wallet - MEDIUM: Unknown dApps with limited approval — monitor c...
AI agents call scan_token_approvals to retrieve information from SolHunt-Solana-Wallet-Intelligence without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes wallet data without modifying it. While the information revealed (token approvals with spending rights) is sensitive and could enable harmful actions if misused, the tool itself performs only read operations.
From the tool's definition Tool performs security scanning and analysis: 'Scan for dApps with spending rights', 'Finds ALL token approvals/delegations', 'rates them by risk', 'Returns: count of approvals by risk, total exposed value, list of dApps'.
Attacks that exploit this kind of access
CRITICAL SECURITY: Scan for dApps with spending rights on your wallet. Finds ALL token approvals/delegations (unlimited and limited) and rates them by risk. Risk Levels: - HIGH: Unknown dApps with unlimited approval — can drain your wallet - MEDIUM: Unknown dApps with limited approval — monitor closely - LOW: Known protocols (Jupiter, Orca, Raydium, etc.) — generally safe Returns: count of approvals by risk, total exposed value, list of dApps with permission to move your tokens, and a security recommendation. Use this BEFORE build_revoke_transactions to identify which approvals to revoke. Also use periodically (monthly) to check for new approvals you forgot about. Free tier: no API key needed. It is categorised as a Read tool in the SolHunt-Solana-Wallet-Intelligence MCP Server, which means it retrieves data without modifying state.
Register the SolHunt-Solana-Wallet-Intelligence MCP server in PolicyLayer and add a rule for scan_token_approvals: 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 SolHunt-Solana-Wallet-Intelligence. Nothing to install.
scan_token_approvals 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 scan_token_approvals 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 scan_token_approvals. 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.
scan_token_approvals is provided by the SolHunt-Solana-Wallet-Intelligence MCP server (shieldspprt/solhunt-recovery). 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 →