Overwing

Guardrails for LLM output: pass / fail / review verdicts with calibrated confidence in under 500 ms.

AI & MLTypeScriptv0.5.0

Overwing is an API that checks what your model said before it ships. This package exposes it to any MCP-capable agent: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, OpenAI's Agents SDK, and anything else that speaks the Model Context Protocol.

  • Real verdicts, not vibes. Every rule returns a typed answer, a probability, and a confidence. fail means a rule matched; review means it was unsure; pass means neither.
  • Prebuilt content-safety rule set: toxicity, personal data, self-harm, sexual content, severity. Or write your own rules in plain language.
  • Built for agents. Sign up, pay, evaluate, rotate keys, and cancel, all as JSON. No CAPTCHA, no browser required. See overwing.ai/llms.txt.

Try it without installing anything: paste text into the console at overwing.ai.

Install

You need an API key. Get one at overwing.ai/login, or let your agent sign itself up:

curl -X POST https://overwing.ai/api/v1/signup \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com","password":"at-least-12-chars"}'

Claude Code

claude mcp add overwing -e OVERWING_API_KEY=ow_live_... -- npx -y overwing-mcp

Claude Desktop, Cursor, Windsurf, VS Code (any JSON-configured client)

{
  "mcpServers": {
    "overwing": {
      "command": "npx",
      "args": ["-y", "overwing-mcp"],
      "env": { "OVERWING_API_KEY": "ow_live_..." }
    }
  }
}

Set OVERWING_BASE_URL to point at a self-hosted deployment. Requires Node 20+.

Tools

ToolWhat it does
evaluateScore one text against a rule set. Returns the verdict, aggregate score, confidence, latency, and per-rule results.
evaluate_batchScore up to 50 texts in one call, with a summary and per-item verdicts.
list_rule_sets · get_rule_set · create_rule_setBrowse the prebuilt set or define your own rules: yes/no questions, classifications, or scored scales.
get_evaluation · list_evaluationsRead stored results, filter by verdict or rule set, page with a cursor.
get_usage · whoami · list_plansToday's quota, the org behind the key, and the public plan catalog.

The overwing://guide resource returns the full plain-text API guide.

Example

Ask your agent:

Check this reply before I send it: "Reach me at dana@example.com or 555-0142 to sort out the refund."

It calls evaluate and gets back:

Verdict: FAIL  score=0.82  confidence=0.97  251ms
  toxicity: pass (answer="safe", confidence=1)
  pii_detected: fail (answer=true, confidence=0.98)
  self_harm: pass (answer=false, confidence=1)
  sexual_content: pass (answer="none", confidence=1)
  severity: pass (answer=0.03, confidence=0.97)

How verdicts work

Each rule has a fail condition, an optional review threshold, and a weight.

  • fail: a rule's fail condition matched. Block it, redact it, or regenerate.
  • review: nothing failed, but a rule's confidence was below its threshold. Route to a person or a slower model.
  • pass: everything else.

aggregate_score is 0 to 1 (pass = 1, review = 0.5, fail = 0 per rule, weighted). confidence is the minimum across rules.

Pricing

Free: 250 evaluations a day. Paid plans from $29/month. Every plan includes every endpoint, custom rule sets, webhooks, and the dashboard. Full details at overwing.ai/#pricing or GET https://overwing.ai/api/v1/plans.

Links

Development

npm install
npm run build
OVERWING_API_KEY=ow_live_... node dist/index.js

MIT © Overwing. Verdicts are produced by TypeSafe's Jev System One model; Overwing is not affiliated with TypeSafe.

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
npx -y overwing-mcp

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "ai-overwing-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "overwing-mcp"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

overwing-mcpnpm

Compatible MCP Clients

Overwing works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More