Build unsigned transactions to swap tokens on Tinyman v2 (Algorand). Returns base64-encoded transactions for signing via wallet.
AI agents invoke swap_txn to trigger actions in Tinyman MCP Server. 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.
swap_txn triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Build unsigned transactions to swap tokens on Tinyman v2 (Algorand). Returns base64-encoded transactions for signing via wallet. It is categorised as a Execute tool in the Tinyman MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tinyman MCP Server MCP server in PolicyLayer and add a rule for swap_txn: 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 Tinyman MCP Server. Nothing to install.
swap_txn 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 swap_txn 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 swap_txn. 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.
swap_txn is provided by the Tinyman MCP Server MCP server (nautilusoss/tinymanmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →