# Regex Explainer

> Explain a regex in plain English and detect catastrophic backtracking risk.

- name: com.gumballtools/regex-explainer
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 89/100 flags: duplicate-repo
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.gumballtools%2Fregex-explainer
- tools: https://api.protogrid.dev/v1/servers/com.gumballtools%2Fregex-explainer/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "regex-explainer": {
      "type": "http",
      "url": "https://regex-explainer.gumballtools.com/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% ~updated-45d-ago -duplicate-repo(16 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 1 of 1 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: explain_regex (destructiveHint, idempotentHint)
- pass `tools.token_cost`: about 472 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 1, about 472 tokens to load them all
- tool set hash: 08addca1c8a9d1d2eb9adb16d47c3367
- badge: [![protogrid quality](https://protogrid.dev/badge/com.gumballtools/regex-explainer.svg)](https://protogrid.dev/servers/com.gumballtools/regex-explainer)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://regex-explainer.gumballtools.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (1)

- `explain_regex`: Explain a regular expression in plain English and detect the failure modes that make patterns dangerous rather than merely wrong.

Use this whenever a regex needs to be read, reviewed, or verified — and ALWAYS before putting a pattern somewhere it will run against untrusted input. The critical check is catastrophic backtracking: a pattern like (a+)+$ is three characters longer than a safe equivalent, looks harmless, and takes minutes of CPU on a 30-character input that almost matches. That makes it a denial-of-service vector. Whether a pattern is vulnerable depends on whether nested quantifiers can match the same characters in more than one way, which is a structural property that is unreliable to judge by reading.

It also flags: missing anchors (an unanchored validator accepts any string that merely CONTAINS a valid value), unescaped dots, character ranges like [A-z] that span punctuation, alternation precedence mistakes where an anchor applies to only one branch, and constructs JavaScript does not support.

Input: `pattern` accepts either a bare pattern or a full /pattern/flags literal. JavaScript syntax; PCRE-only constructs are reported as unsupported rather than guessed at.

Returns: `summary` (one sentence), `steps` (an ordered walkthrough), `warnings` (each with a code, severity, detail, and fix), `flagNotes`, capture group counts and names, and `hasBlockingIssue` — check that flag first. If the pattern cannot be parsed it returns an error naming the position, rather than a plausible-looking explanation of something else.