get_repo_issues
AI agents call get_repo_issues to retrieve information from GitHub Projects MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves issues from a repository—a read-only operation that queries existing data without modification, deletion, or execution. No side effects are expected from calling this tool. Confidence is slightly reduced due to the empty description, but the clear naming convention and sibling context provide strong evidence of its read-only nature.
From the tool's definition Tool name 'get_repo_issues' and sibling tools ('get_project_details', 'get_project_iterations', 'get_repo_prs') all indicate data retrieval operations. Server description states it 'retrieves data from GitHub Projects, including issues'.
Attacks that exploit this kind of access
get_repo_issues. It is categorised as a Read tool in the GitHub Projects MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub Projects MCP Server MCP server in PolicyLayer and add a rule for get_repo_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 GitHub Projects MCP Server. Nothing to install.
get_repo_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 get_repo_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 get_repo_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.
get_repo_issues is provided by the GitHub Projects MCP Server MCP server (jamescalam/github-projects-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 →