Search for specific code patterns in a GitHub repo.
AI agents call tool_search_code to retrieve information from Codelens-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves code information from public GitHub repositories. Searching code patterns is fundamentally a data retrieval operation with no side effects, modifications, or execution capabilities. Even if an AI agent misuses search queries, the worst outcome would be unnecessary API calls or information gathering, which poses minimal risk to the target repository or systems.
From the tool's definition Tool description states 'Search for specific code patterns in a GitHub repo' - a read-only operation that queries and retrieves information without modifying data.
Attacks that exploit this kind of access
Search for specific code patterns in a GitHub repo. It is categorised as a Read tool in the Codelens-MCP MCP Server, which means it retrieves data without modifying state.
Register the Codelens- MCP server in PolicyLayer and add a rule for tool_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 Codelens-MCP. Nothing to install.
tool_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 tool_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 tool_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.
tool_search_code is provided by the Codelens- MCP server (yashkashte5/codelens-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 →