# Unprofane

> Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence.

- name: com.unprofane/unprofane
- version: 0.1.1
- connection class: R1 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.unprofane%2Funprofane
- tools: https://api.protogrid.dev/v1/servers/com.unprofane%2Funprofane/tools

**An agent can connect on its own if it already holds `UNPROFANE_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "unprofane": {
      "type": "http",
      "url": "https://api.unprofane.com/mcp",
      "headers": {
        "Authorization": "Bearer ${UNPROFANE_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${UNPROFANE_TOKEN}`.

## Trust

- hygiene: 80
- liveness: 97
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-93% +updated-3d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### 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: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,359 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 8 tool changes in 30 days
- fail `stability.rug_pull`: 3 tools kept their name but changed most of their description in 30 days; review before trusting them

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

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

- tools: 5, about 2,359 tokens to load them all
- tool set hash: d175ef1cd0b427d0e065c9ad0a88198c
- tools last changed: 2026-10-20T00:18:07.596Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.unprofane/unprofane.svg)](https://protogrid.dev/servers/com.unprofane/unprofane)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `get_usage` added
  - The checks this key's account has used in the current billing period, how many its plan includes and any overage, with the share answered by the rules alone, the model or the cache. Counts up to the last full hour. Read-only and free.
- 2026-10-20 `report_result` added
  - Tell Unprofane a check got it wrong (or right): the result's id, the verdict and, if you know it, the action it should have taken. A person reads every report and corrections ship in a later engine. Writes a report; it changes no result and counts no check.
- 2026-10-20 `check_text` changed (description)
  - before: Decide whether one text should be allowed: profanity, slurs, insults, threats and sexual language, disguised spellings included (sh1t, f.u.c.k, leetspeak, homoglyphs). Returns the action (allow, review, block), the matches with their categories and the tricks used, a one-sentence reason and a censored version. Read-only; counts one check against the plan.
  - after: Decide whether one text should be allowed: profanity, slurs, insults, threats and sexual language, disguised spellings included (sh1t, f.u.c.k, leetspeak, homoglyphs). Returns the action (allow, review, block), the matches with their categories and the tricks used, a one-sentence reason and a censored version. Read-only; counts one check against the plan. If the action is wrong, report it with report_result and the result's id.
- 2026-10-19 `get_integration_snippet` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: A complete, runnable recipe for adding Unprofane to a platform (supabase, clerk, firebase, auth0, better-auth, unity, godot, or plain http) in a language.
  - after: A complete, runnable recipe for adding Unprofane to a platform in a language: code to paste. Use it when asked to add a profanity or username filter to an app. Read-only and free: it checks no text.
- 2026-10-19 `check_batch` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Check up to 100 texts at once. Each item has an id and a text; results come back in order.
  - after: Check up to 100 texts in one call, 30,000 characters in all, with the same settings. Each item has your id and a text; results come back in order, each with its id and either a result (as check_text returns) or an error. Read-only; counts one check per item.
- 2026-10-19 `check_text` changed (title, description, inputSchema, outputSchema, annotations) **meaning changed**
  - before: Decide whether a text should be allowed: profanity, slurs, threats and sexual language, including disguised spellings. Returns the action (allow, review, block), the evidence, a one-sentence reason and a censored version. Use context "username" for names shown publicly.
  - after: Decide whether one text should be allowed: profanity, slurs, insults, threats and sexual language, disguised spellings included (sh1t, f.u.c.k, leetspeak, homoglyphs). Returns the action (allow, review, block), the matches with their categories and the tricks used, a one-sentence reason and a censored version. Read-only; counts one check against the plan.
- 2026-10-17 `check_batch` changed (inputSchema)
- 2026-10-17 `check_text` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/com.unprofane%2Funprofane/changes

## Remotes

- https://api.unprofane.com/mcp (streamable-http, auth api_key ${UNPROFANE_TOKEN}, reachable true, uptime30d 0.9310345)

## Packages

_none_

## Tools (5)

- `check_batch`: Check up to 100 texts in one call, 30,000 characters in all, with the same settings. Each item has your id and a text; results come back in order, each with its id and either a result (as check_text returns) or an error. Read-only; counts one check per item.
- `check_text`: Decide whether one text should be allowed: profanity, slurs, insults, threats and sexual language, disguised spellings included (sh1t, f.u.c.k, leetspeak, homoglyphs). Returns the action (allow, review, block), the matches with their categories and the tricks used, a one-sentence reason and a censored version. Read-only; counts one check against the plan. If the action is wrong, report it with report_result and the result's id.
- `get_integration_snippet`: A complete, runnable recipe for adding Unprofane to a platform in a language: code to paste. Use it when asked to add a profanity or username filter to an app. Read-only and free: it checks no text.
- `get_usage`: The checks this key's account has used in the current billing period, how many its plan includes and any overage, with the share answered by the rules alone, the model or the cache. Counts up to the last full hour. Read-only and free.
- `report_result`: Tell Unprofane a check got it wrong (or right): the result's id, the verdict and, if you know it, the action it should have taken. A person reads every report and corrections ship in a later engine. Writes a report; it changes no result and counts no check.