AI agents call find_estimate 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 retrieves and queries estimate data without modifying, deleting, or executing external operations. It is purely informational in nature, consistent with the Read category. Although estimates are financial artifacts, the tool itself only reads data and does not move money, commit financial obligations, or execute trades.
From the tool's definition Tool name is 'find_estimate' and description states it 'Search for estimates and estimate categories' with ability to search 'across all estimates or within a specific project.' The verb 'search' and lack of any modification or deletion language indicate a…
Attacks that exploit this kind of access
Search for estimates and estimate categories. Can search across all estimates or within a specific project. 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 find_estimate: 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.
find_estimate 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 find_estimate 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 find_estimate. 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.
find_estimate 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 →