github_search_issues
AI agents call github_search_issues to retrieve information from Integrations MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Searching for issues queries GitHub's issue tracker and retrieves results—a classic Read operation with no side effects. Even in a multi-provider platform, searching public or accessible issues cannot create, modify, delete, or execute code. The blast radius is minimal since the operation only fetches data the requester already has permission to view.
From the tool's definition Tool name is 'github_search_issues'; the 'search' verb indicates data retrieval without modification. The description is empty, but the naming pattern is consistent with other Read operations on this server (e.g., airtable_list_records,…
Attacks that exploit this kind of access
github_search_issues. It is categorised as a Read tool in the Integrations MCP MCP Server, which means it retrieves data without modifying state.
Register the Integrations MCP server in PolicyLayer and add a rule for github_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 Integrations MCP. Nothing to install.
github_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 github_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 github_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.
github_search_issues is provided by the Integrations MCP server (shriram-vasudevan/integrations-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 →