Discover a project by its repository URL (supports HTTPS, SSH, with/without .git)
AI agents call discover_project to retrieve information from Planning Game without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves project metadata from a repository URL without altering state or triggering external operations. It is a straightforward read operation with minimal security risk. The severity is low because discovering a project causes no side effects beyond information disclosure, which is typically constrained within the planning/project management domain.
From the tool's definition Tool name and description indicate a discovery/query operation: 'Discover a project by its repository URL'. The action is to retrieve or locate project information based on a URL parameter, with no modification, deletion, or execution of arbitrary code.
Attacks that exploit this kind of access
Discover a project by its repository URL (supports HTTPS, SSH, with/without .git). It is categorised as a Read tool in the Planning Game MCP Server, which means it retrieves data without modifying state.
Register the Planning Game MCP server in PolicyLayer and add a rule for discover_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 Planning Game. Nothing to install.
discover_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 discover_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 discover_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.
discover_project is provided by the Planning Game MCP server (planning-game-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 →