AI agents call github_issues to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and lists existing GitHub issues, which is a read-only operation. It retrieves data without creating, modifying, deleting, or executing any actions. The blast radius of misuse is minimal—an agent could only view issue information that is typically already accessible to authenticated users. No data destruction, financial impact, or code execution is possible.
From the tool's definition Tool name 'github_issues' and description 'List GitHub issues' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List GitHub issues. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for github_issues: 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 VibeServe. Nothing to install.
github_issues 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 github_issues 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 github_issues. 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.
github_issues is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →