Flash-action: stake, unstake, or claim rewards for an LP position in one atomic transaction. Use the action parameter to select the operation. asset_address is the position manager contract — pass the non-staked PM address when staking, or the staked PM address when unstaking. The returned callda...
Part of the Arcadia server.
Free to start. No card required.
AI agents call write.account.stake to retrieve information from Arcadia without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though write.account.stake only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"write.account.stake": {}
}
}See the full Arcadia policy for all 38 tools.
These attack patterns abuse exactly the kind of access write.account.stake gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Flash-action: stake, unstake, or claim rewards for an LP position in one atomic transaction. Use the action parameter to select the operation. asset_address is the position manager contract — pass the non-staked PM address when staking, or the staked PM address when unstaking. The returned calldata is time-sensitive — sign and broadcast within 30 seconds. If the transaction reverts due to price movement, rebuild and sign again immediately (retry at least once before giving up). Tenderly simulation may not be available for this endpoint — verify the position exists with read.account.info before signing.. It is categorised as a Read tool in the Arcadia MCP Server, which means it retrieves data without modifying state.
Register the Arcadia MCP server in PolicyLayer and add a rule for write.account.stake: 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 Arcadia. Nothing to install.
write.account.stake is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the write.account.stake 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 write.account.stake. 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.
write.account.stake is provided by the Arcadia MCP server (arcadia-finance/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 38 Arcadia tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.