Search using glob patterns (*.txt, /*.py) with wildcard support
AI agents call search_by_glob to retrieve information from LocalFS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_by_glob retrieves and returns file paths matching specified patterns without creating, modifying, or deleting any data. It is a read-only filesystem search operation. The glob pattern syntax limits its scope to pattern matching rather than arbitrary code execution. Sandboxing further constrains risk. Severity is low because filesystem search results are informational with no side effects.
From the tool's definition Tool is described as "Search using glob patterns" which is a query operation with no modification capability.
Attacks that exploit this kind of access
Search using glob patterns (*.txt, /*.py) with wildcard support. It is categorised as a Read tool in the LocalFS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LocalFS MCP Server MCP server in PolicyLayer and add a rule for search_by_glob: 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 LocalFS MCP Server. Nothing to install.
search_by_glob 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_by_glob 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_by_glob. 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_by_glob is provided by the LocalFS MCP Server MCP server (mcp-bridge/local-filesystem). 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 →