Search GitHub: repos, code, issues, PRs, commits.
AI agents call gh_search to retrieve information from RedisNexus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries GitHub data across multiple resource types (repositories, code, issues, pull requests, commits) but performs no writes, deletions, executions, or financial transactions. The action verbs are implicitly 'search' and 'list,' which are classic Read operations.
From the tool's definition Tool name 'gh_search' and description 'Search GitHub: repos, code, issues, PRs, commits' indicate read-only query operations with no data modification or side effects.
Attacks that exploit this kind of access
Search GitHub: repos, code, issues, PRs, commits. It is categorised as a Read tool in the RedisNexus MCP Server, which means it retrieves data without modifying state.
Register the RedisNexus MCP server in PolicyLayer and add a rule for gh_search: 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 RedisNexus. Nothing to install.
gh_search 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 gh_search 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 gh_search. 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.
gh_search is provided by the RedisNexus MCP server (rajkumar-madhu/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 →