AI agents call regex_test to retrieve information from Devutils 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 returns structured results (matches, groups, indices) from a test operation. It has no side effects—it neither modifies data, executes code, deletes anything, nor moves money. The operation is purely analytical and informational, fitting the 'Read' category. Severity is low because misuse would only affect the output of a regex test, with negligible blast radius.
From the tool's definition Tool name 'regex_test' and description 'Test a regular expression pattern against an input string. Returns all matches with groups and indices.' indicate a query/test operation that retrieves matching results without modifying, creating, deleting, or…
Attacks that exploit this kind of access
Test a regular expression pattern against an input string. Returns all matches with groups and indices. It is categorised as a Read tool in the Devutils MCP Server, which means it retrieves data without modifying state.
Register the Devutils MCP server in PolicyLayer and add a rule for regex_test: 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 Devutils. Nothing to install.
regex_test 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 regex_test 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 regex_test. 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.
regex_test is provided by the Devutils MCP server (paladini/devutils-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 →