This record as markdown: /tools/abcxz-conviction-fm/export-wallet.md
What export_wallet does on Conviction
AI agents use export_wallet to commit financial operations through Conviction, usually the final step of a payment, billing, or trading workflow. A call moves real money.
Why export_wallet is rated Critical
This server is explicitly financial (trading, positions, revenue pools). An 'export_wallet' tool on such a server almost certainly exports private keys or wallet credentials for an agent that holds or transacts financial assets. Exporting a wallet is a critical financial/security risk: it exposes cryptographic keys that could allow full control over funds.
From the tool's definition 'Export the agent' in context of a server that 'makes money', 'opens positions', and 'captures revenue from competition pools' — wallet export implies extracting private keys or credentials tied to financial assets
Attacks that exploit this kind of access
The rule that runs export_wallet safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Conviction, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For export_wallet, this is the rule to start with:
Any call to export_wallet is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Conviction, apply this rule, and every export_wallet call is checked against it from then on.
Questions about export_wallet
Export the agent. It is categorised as a Financial tool in the Conviction MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Conviction MCP server in PolicyLayer and add a rule for export_wallet: 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 Conviction. Nothing to install.
export_wallet is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the export_wallet 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 export_wallet. 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.
export_wallet is provided by the Conviction MCP server (abcxz/conviction-fm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Conviction, and thousands of servers like it.
Across the catalogue