# Turingate (npm · turingate)

Reverse CAPTCHA for AI agents: prove you're an agent and get a verified, scoped, signed pass.

- Trust score: 70/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `reverse-captcha.onrender.com`: 65/100, [markdown](https://verifymcp.io/servers/rudraneel93-turingate/reverse-captcha.md), [page](https://verifymcp.io/servers/rudraneel93-turingate/reverse-captcha)
- npm · `turingate`: 70/100 (this document), [markdown](https://verifymcp.io/servers/rudraneel93-turingate/turingate.md), [page](https://verifymcp.io/servers/rudraneel93-turingate/turingate)

## Channel facts

- Registry: `npm`
- Package: `turingate`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 306 tokens (~76/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Turingate MCP server?

Turingate runs locally as an npm package, launched with npx -y turingate mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add rudraneel93-turingate -- npx -y turingate mcp
```

### Cursor

```json
{
  "mcpServers": {
    "rudraneel93-turingate": {
      "command": "npx",
      "args": [
        "-y",
        "turingate",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "rudraneel93-turingate": {
      "command": "npx",
      "args": [
        "-y",
        "turingate",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add rudraneel93-turingate -- npx -y turingate mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rudraneel93-turingate": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "turingate",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add rudraneel93-turingate --command npx --arg -y --arg turingate --arg mcp
```

### Hermes

```yaml
mcp_servers:
  rudraneel93-turingate:
    command: "npx"
    args: ["-y", "turingate", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "rudraneel93-turingate": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "turingate",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add rudraneel93-turingate -t stdio -c npx -a -y turingate mcp
```

### Other

```json
{
  "mcpServers": {
    "rudraneel93-turingate": {
      "command": "npx",
      "args": [
        "-y",
        "turingate",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-17 (score 70)

First indexed and scored.

## MCP tools (4)

### `rc_whoami` (~31 tokens)

Show this agent's identity, the human principal it acts for, and its delegated scopes and spend limit.

### `rc_get_challenge` (~166 tokens)

Start a reverse-CAPTCHA challenge to prove you are an AI agent. Returns a list of short tasks. Answer ALL of them yourself and immediately call rc_submit_answers: the time limit is tight (built so humans fail). Do not use other tools in between, except to decode image tasks if you asked for them. Optional images (0-3): hidden-ink image tasks whose question is invisible to humans; each adds 30s. They are saved as local PNG files; decode them with code (the format is in the returned instructions).

Input parameters:

- `images` (integer): number of hidden-ink image tasks (default 0)
- `site` (string): site id (s_...) of the website you want a pass for; the pass is only valid there

### `rc_submit_answers` (~77 tokens)

Submit answers for a challenge. answers maps task id to a short answer string, e.g. {"t1": "42", "t2": "violin"}. On success returns a signed pass token that sites accept as proof this is an accountable agent.

Input parameters:

- `answers` (object, required)
- `challenge_id` (string, required)

### `rc_current_pass` (~32 tokens)

Return the most recent pass token and how to present it to a site (Authorization: AgentPass <token>).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/rudraneel93-turingate/turingate#diagnostics

## Score history

- 2026-11-21: 70
- 2026-11-20: 70
- 2026-11-19: 70
- 2026-11-18: 70
- 2026-11-17: 70

## Common questions

### What is the Turingate MCP server?

Turingate is an MCP server listed in the public MCP registry as io.github.rudraneel93/turingate. Reverse CAPTCHA for AI agents: prove you're an agent and get a verified, scoped, signed pass. This page covers its npm package (turingate).

### Is the Turingate MCP server safe to use?

Turingate scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Turingate MCP server expose?

Turingate exposes 4 tools: rc_whoami, rc_get_challenge, rc_submit_answers, rc_current_pass. Their descriptions and schemas cost roughly 306 tokens of context every time the server is loaded.

### Is the Turingate MCP server still maintained?

Turingate is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Turingate MCP server under?

Turingate declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Turingate MCP server?

VerifyMCP ran 15 checks on Turingate, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Turingate: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/turingate
- Socket report: https://socket.dev/npm/package/turingate
- Repository: https://github.com/rudraneel93/turingate-sdk
- Website: https://reverse-captcha.onrender.com/
- Changelog RSS feed: https://verifymcp.io/servers/rudraneel93-turingate/turingate.xml
- Changelog JSON feed: https://verifymcp.io/servers/rudraneel93-turingate/turingate/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/rudraneel93-turingate/turingate.json
- HTML version of this page: https://verifymcp.io/servers/rudraneel93-turingate/turingate
