Get details of an AgentFund project by ID. Returns funder address, agent address, total/released amounts, milestone progress, and status (Active/Completed/Cancelled).
AI agents call agentfund_get_project to retrieve information from AgentFund MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries project data without side effects. While the AgentFund server overall manages financial escrow mechanisms, this specific tool is purely informational—it reads and returns existing project details. The blast radius of misuse is minimal: an agent querying project details cannot cause financial harm, data loss, or unintended operations. Classification as Read is appropriate.
From the tool's definition Tool description explicitly states it 'Get details' and 'Returns' project information (funder address, agent address, amounts, milestone progress, status). No state modification, data creation, deletion, execution, or financial transaction described.
Attacks that exploit this kind of access
Get details of an AgentFund project by ID. Returns funder address, agent address, total/released amounts, milestone progress, and status (Active/Completed/Cancelled). It is categorised as a Read tool in the AgentFund MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AgentFund MCP Server MCP server in PolicyLayer and add a rule for agentfund_get_project: 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_get_project 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 agentfund_get_project 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_get_project. 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_get_project 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 →