search_issues
AI agents call search_issues to retrieve information from GitHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve data without modifying or deleting anything. While the description is empty, the naming convention and context of sibling tools strongly indicate this is a read-only query function. The blast radius of misuse is minimal—an agent might retrieve unwanted issue information but cannot cause data loss or trigger actions.
From the tool's definition Tool name 'search_issues' indicates a query/search operation. The sibling tools on this server (create_issue, create_pr_review, create_gist, etc.) show this server performs various write and execute actions; search_issues is clearly the read counterpart for…
Attacks that exploit this kind of access
search_issues. It is categorised as a Read tool in the GitHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GitHub MCP Server MCP server in PolicyLayer and add a rule for search_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 MCP Server. Nothing to install.
search_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 search_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 search_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.
search_issues is provided by the GitHub MCP Server MCP server (software-engineer-mj/github-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 →