AI agents use DEPLOY_TOKEN to commit financial operations through Solana Agent Kit MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Deploying a token on a blockchain is a financially significant and largely irreversible action. It commits on-chain resources, may involve SOL fees, and creates a new financial instrument. Given the financial nature of token creation and the irreversibility of blockchain state changes, this falls under Financial (most severe applicable category).
From the tool's definition "Deploy a new token on Solana" — creates and deploys a new blockchain token asset on the Solana network
Documented attack patterns abuse exactly the kind of access DEPLOY_TOKEN gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Solana Agent Kit MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for DEPLOY_TOKEN:
{
"version": "1",
"default": "deny",
"tools": {
"DEPLOY_TOKEN": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
}Any call to DEPLOY_TOKEN is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Deploy a new token on Solana. It is categorised as a Financial tool in the Solana Agent Kit MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Solana Agent Kit MCP Server MCP server in PolicyLayer and add a rule for DEPLOY_TOKEN: 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 Solana Agent Kit MCP Server. Nothing to install.
DEPLOY_TOKEN is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the DEPLOY_TOKEN 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 DEPLOY_TOKEN. 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.
DEPLOY_TOKEN is provided by the Solana Agent Kit MCP Server MCP server (sendaifun/solana-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Solana Agent Kit MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Solana Agent Kit MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.