AI agents invoke unwrap_wedu to trigger actions in EDUCHAIN Agent Kit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Unwrapping a wrapped token is an on-chain operation that executes a smart contract call, converting WEDU back to native EDU. This is an irreversible blockchain transaction that modifies token balances, making it Execute-level. While it doesn't delete data, it triggers an external financial operation on-chain. Severity is high because a misuse could result in unintended token conversions affecting user funds.
From the tool's definition Unwrap WEDU (Wrapped EDU) to EDU — triggers an on-chain token conversion transaction
Documented attack patterns abuse exactly the kind of access unwrap_wedu gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and EDUCHAIN Agent Kit, and nothing reaches the server without passing your rules. This is the rule we recommend for unwrap_wedu:
{
"version": "1",
"default": "deny",
"tools": {
"unwrap_wedu": {
"limits": [
{
"counter": "unwrap_wedu_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}unwrap_wedu stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Unwrap WEDU (Wrapped EDU) to EDU. It is categorised as a Execute tool in the EDUCHAIN Agent Kit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the EDUCHAIN Agent Kit MCP server in PolicyLayer and add a rule for unwrap_wedu: 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 EDUCHAIN Agent Kit. Nothing to install.
unwrap_wedu is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the unwrap_wedu 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 unwrap_wedu. 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.
unwrap_wedu is provided by the EDUCHAIN Agent Kit MCP server (sailfish-finance/educhain-ai-agent-kit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from EDUCHAIN Agent Kit, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 EDUCHAIN Agent Kit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.