53 tools. 12 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Financial operations (request_withdraw_stake, transfer_objects, transfer_sui) can move real money. An agent caught in a loop could drain accounts before anyone notices.
Write operations (create_wallet, import_wallet, merge_coins) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (dry_run_transaction) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
request_withdraw_stake:
rules:
- action: deny Financial tools should be explicitly enabled per use case, not open by default.
create_wallet:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
cetus_get_pool:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Sui server exposes 3 financial tools including request_withdraw_stake, transfer_objects, transfer_sui. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. Intercept lets you block financial tools by default or set per-tool rate limits.
The Sui server has 8 write tools including create_wallet, import_wallet, merge_coins. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
53 tools across 4 categories: Execute, Financial, Read, Write. 41 are read-only. 12 can modify, create, or delete data.
One line change. Instead of running the Sui server directly, prefix it with Intercept: intercept -c io-github-expertvagabond-sui-mcp-server.yaml -- npx -y @sui-mcp-server. Download a pre-built policy from policylayer.com/policies/io-github-expertvagabond-sui-mcp-server and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.