regex
Test/replace regex patterns (200 sats/call; free tier 100 calls/mo)
This record as markdown: /tools/com-thetempleofdoom-hyperion-hyperion/regex.md
What regex does on Hyperion
AI agents call regex to retrieve information from Hyperion without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Input text to search against. |
flags | string | — | Flags like "g", "i", "m" (default "g"). |
pattern | string | Yes | Regex pattern string without slashes. |
replacement | string | — | Optional replacement text string. |
Parameters from the server's own tool schema.
Why regex is rated Low
Even though regex only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs regex safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hyperion, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For regex, this is the rule to start with:
regex is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hyperion, apply this rule, and every regex call is checked against it from then on.
Questions about regex
Test/replace regex patterns (200 sats/call; free tier 100 calls/mo). It is categorised as a Read tool in the Hyperion MCP Server, which means it retrieves data without modifying state.
regex accepts 4 parameters: text, flags, pattern, replacement. Required: text, pattern. The full parameter table on this page comes from the server's own tool schema.
Register the Hyperion MCP server in PolicyLayer and add a rule for regex: 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 Hyperion. Nothing to install.
regex 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 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. 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 is provided by the Hyperion MCP server (https://hyperion.thetempleofdoom.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hyperion, and thousands of servers like it.
This server
Across the catalogue