This record as markdown: /tools/aarna-ai-atv/build-unstake-tx.md
What build_unstake_tx does on Atv
AI agents invoke build_unstake_tx to trigger actions in Atv. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
stakeIndex | string | — | 0-indexed position in the user's stake array to unstake from |
userAddress | string | — | EVM address of the staker |
vaultAddress | string | — | Vault contract address |
unstakeAmount | string | — | Human-readable vault token amount to unstake, e.g. '100' |
Parameters from the server's own tool schema.
Why build_unstake_tx is rated High
This tool belongs in Execute rather than Write because: (1) it triggers external blockchain operations via transaction building for a financial protocol, (2) unstaking is irreversible in the sense that once submitted, the blockchain state changes and tokens are moved, and (3) it operates on a timelock contract, which suggests time-sensitive state transitions.
From the tool's definition Tool description states it 'Build the transaction step to unstake vault tokens from a timelock contract.' The verb 'build' combined with 'transaction' and 'unstake' indicates this tool constructs and prepares blockchain transactions that move or unlock…
Attacks that exploit this kind of access
The rule that runs build_unstake_tx safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Atv, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build_unstake_tx, this is the rule to start with:
build_unstake_tx 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Atv, apply this rule, and every build_unstake_tx call is checked against it from then on.
Questions about build_unstake_tx
Build the transaction step to unstake vault tokens from a timelock contract. It is categorised as a Execute tool in the Atv MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
build_unstake_tx accepts 4 parameters: stakeIndex, userAddress, vaultAddress, unstakeAmount. The full parameter table on this page comes from the server's own tool schema.
Register the Atv MCP server in PolicyLayer and add a rule for build_unstake_tx: 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 Atv. Nothing to install.
build_unstake_tx 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 build_unstake_tx 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 build_unstake_tx. 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.
build_unstake_tx is provided by the Atv MCP server (aarna-ai/atv). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Atv, and thousands of servers like it.
This server
Across the catalogue