List all roles that are available from GitHub repositories (directory-based roles). These roles must be cloned on the Ludus server before installation. Returns: Dictionary with available role repositories and their GitHub URLs Example: result = await list_role_repositories()
AI agents call list_role_repositories to retrieve information from Ludus FastMCP 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 information about available Ansible role repositories without modifying, deleting, or executing any operations. It simply returns a dictionary of available roles and their GitHub URLs. No data is created, modified, or deleted, and no external commands are executed. This is a classic Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'list_role_repositories' and description states it 'List all roles that are available from GitHub repositories' and 'Returns: Dictionary with available role repositories and their GitHub URLs'.
Documented attack patterns abuse exactly the kind of access list_role_repositories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ludus FastMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list_role_repositories:
{
"version": "1",
"default": "deny",
"tools": {
"list_role_repositories": {}
}
}list_role_repositories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all roles that are available from GitHub repositories (directory-based roles). These roles must be cloned on the Ludus server before installation. Returns: Dictionary with available role repositories and their GitHub URLs Example: result = await list_role_repositories(). It is categorised as a Read tool in the Ludus FastMCP MCP Server, which means it retrieves data without modifying state.
Register the Ludus Fast MCP server in PolicyLayer and add a rule for list_role_repositories: 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 Ludus FastMCP. Nothing to install.
list_role_repositories 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_role_repositories 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_role_repositories. 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_role_repositories is provided by the Ludus Fast MCP server (tjnull/ludus-fastmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 201 Ludus FastMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
201 Ludus FastMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.