Execute a quote. Call haiku_get_quote first, then choose a path: • Path A — Self-contained (WALLET_PRIVATE_KEY set): pass quoteId, sourceChainId, permit2SigningPayload + bridgeSigningPayload (if present in the quote), and approvals. Haiku signs Permit2/bridge internally, sends any approvals on-ch...
Part of the Haiku DeFi MCP MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke haiku_execute to trigger processes or run actions in Haiku DeFi MCP. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
haiku_execute can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
haiku_execute:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full Haiku DeFi MCP policy for all 7 tools.
Agents calling execute-class tools like haiku_execute have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
haiku_execute is one of the high-risk operations in Haiku DeFi MCP. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Execute a quote. Call haiku_get_quote first, then choose a path: • Path A — Self-contained (WALLET_PRIVATE_KEY set): pass quoteId, sourceChainId, permit2SigningPayload + bridgeSigningPayload (if present in the quote), and approvals. Haiku signs Permit2/bridge internally, sends any approvals on-chain, and broadcasts. Returns tx hash. • Path B — External wallet (no WALLET_PRIVATE_KEY): broadcast: false is required. First broadcast any approvals from the quote via your wallet MCP (each is a {to, data} transaction). Then call haiku_prepare_signatures if signatures are needed → sign via wallet MCP → call haiku_execute with quoteId, sourceChainId, the signatures, and broadcast: false. Returns { transaction: { to, data, value, chainId } } — broadcast transaction via your wallet MCP. Always pass sourceChainId from the quote response.. It is categorised as a Execute tool in the Haiku DeFi MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Add a rule in your Intercept YAML policy under the tools section for haiku_execute. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Haiku DeFi MCP MCP server.
haiku_execute 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 haiku_execute rule in your Intercept 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 Intercept policy for haiku_execute. 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.
haiku_execute is provided by the Haiku DeFi MCP MCP server (haiku-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.