sweep_agent

Sweep funds from agent back to operator balance. REQUIRES OPERATOR KEY.

SERVERLightning Wallet SOURCElightning-wallet-mcp
Critical RISK CLASS
Category Financial
Parameters 00 required
Recommended Approval-gatedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-lightningfaucet-lightning-wallet-mcp/sweep-agent.md

What sweep_agent does on Lightning Wallet

AI agents use sweep_agent to commit financial operations through Lightning Wallet, usually the final step of a payment, billing, or trading workflow. A call moves real money.

Why sweep_agent is rated Critical

This tool transfers financial assets (Bitcoin via Lightning Network) from one wallet/account to another. Even though it moves funds 'back to operator,' it is a financial transfer operation that could be misused to drain an agent's wallet. Requires an operator key, indicating elevated privilege. Misuse could result in loss of funds or unauthorized fund movements, warranting critical severity.

From the tool's definition 'Sweep funds from agent back to operator balance' — moves Bitcoin/Lightning funds between accounts

Questions about sweep_agent

What does the sweep_agent tool do? +

Sweep funds from agent back to operator balance. REQUIRES OPERATOR KEY. It is categorised as a Financial tool in the Lightning Wallet MCP Server, which means it involves financial transactions. Block by default and require explicit approval.

How do I enforce a policy on sweep_agent? +

Register the Lightning Wallet MCP server in PolicyLayer and add a rule for sweep_agent: 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 Lightning Wallet. Nothing to install.

What risk level is sweep_agent? +

sweep_agent is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit sweep_agent? +

Yes. Add a rate_limit block to the sweep_agent 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.

How do I block sweep_agent completely? +

Set action: deny in the PolicyLayer policy for sweep_agent. 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.

What MCP server provides sweep_agent? +

sweep_agent is provided by the Lightning Wallet MCP server (lightning-wallet-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Lightning Wallet, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Lightning Wallet's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.