Lists all GitHub repositories connected to your Jules account.
AI agents call jules_list_sources to retrieve information from Jules MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about connected repositories without modifying, deleting, or executing anything. It is a pure read operation with minimal blast radius—an agent listing repositories causes no harm unless combined with subsequent write or destructive actions on those repositories.
From the tool's definition Tool name 'jules_list_sources' and description 'Lists all GitHub repositories connected to your Jules account' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Lists all GitHub repositories connected to your Jules account. It is categorised as a Read tool in the Jules MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jules MCP Server MCP server in PolicyLayer and add a rule for jules_list_sources: 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 Jules MCP Server. Nothing to install.
jules_list_sources 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 jules_list_sources 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 jules_list_sources. 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.
jules_list_sources is provided by the Jules MCP Server MCP server (streetquant/jules-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 →