AI agents call list_proposals to retrieve information from JoeMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves proposal data without creating, modifying, deleting, or executing any operations. It has no side effects and returns minimal metadata. The recommendation to use 'discover or search to find proposals and get full details' further confirms this is a simple list/read operation. Severity is low because data retrieval with no side effects presents minimal risk if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Get a minimal list of proposals' and 'Returns only name, id, and projectId for each proposal'.
Attacks that exploit this kind of access
Get a minimal list of proposals with optional project filtering. Returns only name, id, and projectId for each proposal. Use discover or search to find proposals and get full details. It is categorised as a Read tool in the JoeMCP MCP Server, which means it retrieves data without modifying state.
Register the Joe MCP server in PolicyLayer and add a rule for list_proposals: 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 JoeMCP. Nothing to install.
list_proposals 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 list_proposals 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 list_proposals. 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.
list_proposals is provided by the Joe MCP server (lumberjack-so/joemcp). 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 →