List issues for a repository (pull requests excluded): number, title, state, author, labels, comment count, and created/updated times. Filter by state (open/closed/all) and labels; paginate. Read-only; no caller key needed.
AI agents call github.issues to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and filters existing issue data from a repository. It performs no modifications, deletions, code execution, or financial operations. The explicit 'Read-only' designation confirms it has no side effects. Severity is low because the information returned is typically publicly available on GitHub and poses minimal risk even if misused.
From the tool's definition Tool description explicitly states 'List issues for a repository' and 'Read-only; no caller key needed.' It retrieves metadata (number, title, state, author, labels, comment count, created/updated times) with filtering and pagination—all query operations with…
Attacks that exploit this kind of access
List issues for a repository (pull requests excluded): number, title, state, author, labels, comment count, and created/updated times. Filter by state (open/closed/all) and labels; paginate. Read-only; no caller key needed. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the 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 Mcp. 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 MCP server (@2sio/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 →