Scan a directory for git repos and return suggested project entries.
AI agents call auto_discover to retrieve information from Studio Catharsis Universal Project Coordinator MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool scans a directory and returns information about discovered git repositories. This is a read/query operation with no side effects. Severity is medium rather than low because scanning directory structures and git repos could reveal sensitive information about the filesystem layout, repository names, and project structure if misused by an agent.
From the tool's definition Scan a directory for git repos and return suggested project entries
Attacks that exploit this kind of access
Scan a directory for git repos and return suggested project entries. It is categorised as a Read tool in the Studio Catharsis Universal Project Coordinator MCP MCP Server, which means it retrieves data without modifying state.
Register the Studio Catharsis Universal Project Coordinator MCP server in PolicyLayer and add a rule for auto_discover: 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 Studio Catharsis Universal Project Coordinator MCP. Nothing to install.
auto_discover 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 auto_discover 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 auto_discover. 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.
auto_discover is provided by the Studio Catharsis Universal Project Coordinator MCP server (studio-catharsis-creative-lab/project_com_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 →