Search code across GitHub — great for finding usage examples.
AI agents call github_search_code to retrieve information from Mcp Everything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries GitHub's code search API to retrieve code snippets and examples. It does not create, modify, delete, or execute any code—it only searches and returns results. This is a standard read operation with minimal risk. The severity is low because misuse would only result in retrieving publicly available information, with no capability to alter system state or access restricted data.
From the tool's definition Tool description states 'Search code across GitHub', which is a retrieval operation. The phrase 'great for finding usage examples' confirms it is read-only with no side effects.
Attacks that exploit this kind of access
Search code across GitHub — great for finding usage examples. It is categorised as a Read tool in the Mcp Everything MCP Server, which means it retrieves data without modifying state.
Register the Mcp Everything MCP server in PolicyLayer and add a rule for github_search_code: 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 Everything. Nothing to install.
github_search_code 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_code 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_code. 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_code is provided by the Mcp Everything MCP server (wellix260/mcp-everything). 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 →