AI agents call find_project 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 is a straightforward query/search tool that retrieves project data without side effects. It does not create, modify, delete, or execute any operations—it only reads and returns matching project information. The low severity reflects the minimal risk from misuse of a read-only data retrieval function.
From the tool's definition Tool performs a search operation that 'Returns matching projects with basic info' with no mention of modification, deletion, or execution capabilities. The verb 'find' and 'search' indicate retrieval-only functionality.
Attacks that exploit this kind of access
Search for projects by name, client name, or other attributes. Returns matching projects with basic info. 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_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 JoeMCP. Nothing to install.
find_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 find_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 find_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.
find_project 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 →