Регулярный поиск по всем файлам проектов
AI agents call code_grep to retrieve information from Booster MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs pattern matching and searches across codebase files without modifying, executing, or deleting anything. It retrieves information only. The operation has no side effects and fits the Read category. Severity is low because unauthorized regex searches on code pose minimal risk compared to modification or execution capabilities.
From the tool's definition Tool name 'code_grep' and description 'Регулярный поиск по всем файлам проектов' (Regular search across all project files) indicate a search/query operation.
Attacks that exploit this kind of access
Регулярный поиск по всем файлам проектов. It is categorised as a Read tool in the Booster MCP MCP Server, which means it retrieves data without modifying state.
Register the Booster MCP server in PolicyLayer and add a rule for code_grep: 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 Booster MCP. Nothing to install.
code_grep 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 code_grep 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 code_grep. 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.
code_grep is provided by the Booster MCP server (neuroghostdev/booster_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 →