approve_token_spending · SEI MCP Server V2 MCP

WHAT IT DOES

What approve_token_spending does on SEI MCP Server V2

AI agents use approve_token_spending to create or update resources in SEI MCP Server V2 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SEI MCP Server V2 environment.

WHY IT NEEDS A POLICY

Why approve_token_spending needs a policy

This tool creates or modifies token allowance state on-chain, which is a Write operation (reversible via revoke). However, the severity is high rather than medium because approving token spending is a critical financial authorization that, if misused by an agent (e.g., approving an attacker's address or excessive amounts), could lead to token theft.

From the tool's definition Approve another address to spend your ERC20 tokens — this modifies the allowance state of a token contract, granting spending permissions that are reversible but have significant financial implications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

approve_token_spending Rate-limited

approve_token_spending stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "approve_token_spending": {
      "limits": [
        {
          "counter": "approve_token_spending_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches SEI MCP Server V2, so you can run agents against it safely.

FAQ

Questions about approve_token_spending

What does the approve_token_spending tool do? +

Approve another address to spend your ERC20 tokens. It is categorised as a Write tool in the SEI MCP Server V2 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on approve_token_spending? +

Register the SEI MCP Server V2 MCP server in PolicyLayer and add a rule for approve_token_spending: 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 SEI MCP Server V2. Nothing to install.

What risk level is approve_token_spending? +

approve_token_spending is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit approve_token_spending? +

Yes. Add a rate_limit block to the approve_token_spending 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.

How do I block approve_token_spending completely? +

Set action: deny in the PolicyLayer policy for approve_token_spending. 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.

What MCP server provides approve_token_spending? +

approve_token_spending is provided by the SEI MCP Server V2 MCP server (testinguser1111111/sei-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.