AI agents call regex_search to retrieve information from Kontexta without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search/query operation that retrieves data matching a regex pattern. It has no side effects—it does not create, modify, delete, or execute anything. The scope parameters (project, KB, or all) determine the search boundaries but do not change the fundamental read-only nature. Low severity because misuse would only expose matching file contents, not execute code or destroy data.
From the tool's definition Tool description explicitly states it performs regex matching against file bodies and 'return[s] per-file hits with line numbers'. The verb 'Match' and 'return' indicate retrieval only, with no modification, deletion, or execution capability.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Match a JS regex against the body of every file in scope (project, KB, or all) and return per-file hits with line numbers. Slower than FTS. It is categorised as a Read tool in the Kontexta MCP Server, which means it retrieves data without modifying state.
Register the Kontexta MCP server in PolicyLayer and add a rule for regex_search: 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 Kontexta. Nothing to install.
regex_search 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_search 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_search. 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_search is provided by the Kontexta MCP server (safiyu/kontexta). 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 →