Get all proposals for a specific DAO
AI agents call getProposals to retrieve information from Futarchy MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns proposal data without modifying, deleting, or executing any operations. It is a read-only operation that retrieves information from the Futarchy protocol. The blast radius of misuse is minimal — an attacker could only access proposal information that may already be public or available to the querying user.
From the tool's definition Tool name is 'getProposals' and description states 'Get all proposals for a specific DAO' — a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all proposals for a specific DAO. It is categorised as a Read tool in the Futarchy MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Futarchy MCP Server MCP server in PolicyLayer and add a rule for getProposals: 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 Futarchy MCP Server. Nothing to install.
getProposals 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 getProposals 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 getProposals. 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.
getProposals is provided by the Futarchy MCP Server MCP server (tanmay4l/futarchymcpserver). 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 →