AI agents call dev_grep to retrieve information from Jt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
grep is a standard read-only search utility. The tool retrieves and filters file contents matching a pattern but does not create, modify, delete, or execute anything. It has minimal blast radius even if misused by an agent—worst case is exposure of sensitive data already present in accessible files, which is a read/disclosure risk, not execution or destruction.
From the tool's definition Tool name is 'dev_grep' and description states it 'Search[es] file contents for a pattern (regex or literal) within a project directory.' This is a search/query operation with no side effects.
Attacks that exploit this kind of access
Search file contents for a pattern (regex or literal) within a project directory. It is categorised as a Read tool in the Jt MCP Server, which means it retrieves data without modifying state.
Register the Jt MCP server in PolicyLayer and add a rule for dev_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 Jt. Nothing to install.
dev_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 dev_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 dev_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.
dev_grep is provided by the Jt MCP server (@houkasaurusrex/jt-mcp-server). 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 →