Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

claude mcp add --transport http unprofane https://api.unprofane.com/mcp --header "Authorization: Bearer ${UNPROFANE_TOKEN}"

[mcp_servers.unprofane]
url = "https://api.unprofane.com/mcp"
bearer_token_env_var = "UNPROFANE_TOKEN"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "unprofane": {
      "type": "remote",
      "url": "https://api.unprofane.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer {env:UNPROFANE_TOKEN}"
      }
    }
  }
}

{
  "mcpServers": {
    "unprofane": {
      "type": "http",
      "url": "https://api.unprofane.com/mcp",
      "headers": {
        "Authorization": "Bearer ${UNPROFANE_TOKEN}"
      }
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=unprofane&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnVucHJvZmFuZS5jb20vbWNwIiwiaGVhZGVycyI6eyJBdXRob3JpemF0aW9uIjoiQmVhcmVyICR7VU5QUk9GQU5FX1RPS0VOfSJ9fQ%3D%3D"
}

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

{
  "mcpServers": {
    "unprofane": {
      "httpUrl": "https://api.unprofane.com/mcp",
      "headers": {
        "Authorization": "Bearer ${UNPROFANE_TOKEN}"
      }
    }
  }
}

extensions:
  "unprofane":
    enabled: true
    name: "unprofane"
    type: streamable_http
    uri: "https://api.unprofane.com/mcp"
    headers:
      "Authorization": "Bearer ${UNPROFANE_TOKEN}"
    timeout: 300

Placeholders to fill from your own secret store: ${UNPROFANE_TOKEN}. The registry never accepts secret values.

Quality 75 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations5 of 5 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,359 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability25 · weight 15

warn
stability.changes8 tool changes in 30 days
fail
stability.rug_pull3 tools kept their name but changed most of their description in 30 days; review before trusting them

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 2,359 tokens to load them all · tool set d175ef1cd0b4 · tools last changed 2026-10-20 · checked 2026-10-20 10:03 UTC

Tool changes

2026-10-20get_usageadded
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.
2026-10-20report_resultadded
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.
2026-10-20check_textchangeddescription
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 · 86% of words in common
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.
2026-10-19get_integration_snippetchangedtitle, description, input schema, annotationsmeaning 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 · 29% of words in common
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.
2026-10-19check_batchchangedtitle, description, input schema, output schema, annotationsmeaning changed
before
Check up to 100 texts at once. Each item has an id and a text; results come back in order.
after · 43% of words in common
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.
2026-10-19check_textchangedtitle, description, input schema, output schema, annotationsmeaning 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 · 46% of words in common
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.
2026-10-17check_batchchangedinput schema
2026-10-17check_textchangedinput schema

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 82 / 100

no-repository

provenance55

liveness97

freshness100

hygiene80

+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. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.unprofane.com/mcp` streamable-http	api_key `${UNPROFANE_TOKEN}`	yes	93%	883 ms	2025-06-18	2026-10-20

Tools (5)

`check_batch`read-only	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`read-only	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`read-only	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`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.unprofane/unprofane",
  "icons": [
    {
      "src": "https://unprofane.com/logo.png",
      "sizes": [
        "512x512"
      ],
      "mimeType": "image/png"
    }
  ],
  "title": "Unprofane",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.unprofane.com/mcp",
      "type": "streamable-http",
      "headers": [
        {
          "name": "Authorization",
          "isSecret": true,
          "isRequired": true,
          "description": "Bearer up_live_… (an Unprofane API key from https://unprofane.com/app/keys/)"
        }
      ]
    }
  ],
  "version": "0.1.1",
  "websiteUrl": "https://unprofane.com/docs/mcp/",
  "description": "Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence."
}