Semantic search over the indexed codebase. Use this INSTEAD of Grep
AI agents call search_repo to retrieve information from Code Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches codebase information via semantic indexing. It performs no data modification, deletion, code execution, or side effects—it is purely a read operation. The emphasis on using it 'INSTEAD of Grep' further confirms it is a search/query tool. Low severity reflects minimal risk from misuse; at worst an agent retrieves incorrect or sensitive code patterns, but cannot modify or execute.
From the tool's definition Tool is explicitly described as 'Semantic search over the indexed codebase' with instruction to use it 'INSTEAD of Grep'. The name 'search_repo' and description indicate retrieval/query of indexed code data without modification or execution.
Attacks that exploit this kind of access
Semantic search over the indexed codebase. Use this INSTEAD of Grep. It is categorised as a Read tool in the Code Context MCP Server, which means it retrieves data without modifying state.
Register the Code Context MCP server in PolicyLayer and add a rule for search_repo: 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 Code Context. Nothing to install.
search_repo 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_repo 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_repo. 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_repo is provided by the Code Context MCP server (nachogeinfor-ops/code-context). 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 →