Generate transaction data for creating a new AgentFund fundraise. YOU provide your agent address (where funds go) and milestones. A FUNDER will execute this transaction and send the ETH. Use this when you want to propose a project for funding.
AI agents use agentfund_create_fundraise 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 creates fundraise proposals on the Base chain that result in ETH being sent to an agent address via escrow. While the AI agent generates the transaction data rather than directly moving funds, it initiates a financial commitment/obligation involving real ETH transfers on a blockchain. This falls squarely in the Financial category as it sets up the conditions for fund movement.
From the tool's definition 'Generate transaction data for creating a new AgentFund fundraise', 'A FUNDER will execute this transaction and send the ETH', 'propose a project for funding', 'milestone-based escrow management'
Attacks that exploit this kind of access
Generate transaction data for creating a new AgentFund fundraise. YOU provide your agent address (where funds go) and milestones. A FUNDER will execute this transaction and send the ETH. Use this when you want to propose a project for funding. 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_create_fundraise: 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_create_fundraise 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_create_fundraise 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_create_fundraise. 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_create_fundraise 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 →