Search across all script sources using patterns. Like ripgrep for your Roblox project. Args: - pattern (string): Search pattern (Lua pattern or regex) - useRegex (boolean, optional): Use JavaScript regex instead of Lua patterns (default: false) - contextLines (number, optional): Lines of context ...
AI agents call grep_scripts to retrieve information from Melo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only operations on script sources within a Roblox project. It searches and retrieves matching patterns from scripts but does not create, modify, delete, or execute any code. The tool is analogous to standard code search utilities (ripgrep) which are fundamentally information retrieval operations.
From the tool's definition Tool description states 'Search across all script sources using patterns' and 'Like ripgrep for your Roblox project.' The functionality is purely searching/querying existing script content with configurable context and filtering options.
Attacks that exploit this kind of access
Search across all script sources using patterns. Like ripgrep for your Roblox project. Args: - pattern (string): Search pattern (Lua pattern or regex) - useRegex (boolean, optional): Use JavaScript regex instead of Lua patterns (default: false) - contextLines (number, optional): Lines of context around matches (default: 2) - scriptType (string, optional): Filter to. It is categorised as a Read tool in the Melo MCP Server, which means it retrieves data without modifying state.
Register the Melo MCP server in PolicyLayer and add a rule for grep_scripts: 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 Melo. Nothing to install.
grep_scripts 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 grep_scripts 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 grep_scripts. 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.
grep_scripts is provided by the Melo MCP server (yannyhl/linkedsword-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 →