Generate a milestone release request. After completing work for a milestone, use this to generate the transaction the funder needs to sign to release your funds.
AI agents use agentfund_generate_release_request to commit financial operations through AgentFund MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly triggers a blockchain financial transaction request to release funds held in escrow. While the funder must sign, the AI agent is generating and initiating the payment release request, which constitutes committing a financial obligation/movement of funds. Misuse could cause unauthorized or premature fund releases from escrow contracts, making this a critical financial risk.
From the tool's definition 'Generate a milestone release request' and 'generate the transaction the funder needs to sign to release your funds' — this tool initiates a financial transaction to release escrowed funds from a milestone-based escrow contract on the Base chain.
Attacks that exploit this kind of access
Generate a milestone release request. After completing work for a milestone, use this to generate the transaction the funder needs to sign to release your funds. It is categorised as a Financial tool in the AgentFund MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the AgentFund MCP Server MCP server in PolicyLayer and add a rule for agentfund_generate_release_request: 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 AgentFund MCP Server. Nothing to install.
agentfund_generate_release_request 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 agentfund_generate_release_request 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 agentfund_generate_release_request. 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.
agentfund_generate_release_request is provided by the AgentFund MCP Server MCP server (riothegreat-ai/agentfund-mcp). 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 →