# TuringCorp (remote · mcp.turingcorp.net)

A decision model for the calls that don't have a right answer. The better option, with a reason.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-27

## Components

- remote · `mcp.turingcorp.net`: 73/100 (this document), [markdown](https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp.md), [page](https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp)

## Channel facts

- Endpoint: `https://mcp.turingcorp.net/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-09-27.

- **Endpoint Security**: 86/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1025 tokens (~512/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability check failed: schema churn in the 5 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 1 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (50% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

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

TuringCorp is a hosted endpoint at https://mcp.turingcorp.net/mcp, so there is nothing to install locally. 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 --transport http net-turingcorp-mcp-decider 'https://mcp.turingcorp.net/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "net-turingcorp-mcp-decider": {
      "url": "https://mcp.turingcorp.net/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "net-turingcorp-mcp-decider": {
      "type": "http",
      "url": "https://mcp.turingcorp.net/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.net-turingcorp-mcp-decider]
url = "https://mcp.turingcorp.net/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "net-turingcorp-mcp-decider": {
      "type": "remote",
      "url": "https://mcp.turingcorp.net/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add net-turingcorp-mcp-decider --url 'https://mcp.turingcorp.net/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  net-turingcorp-mcp-decider:
    url: "https://mcp.turingcorp.net/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "net-turingcorp-mcp-decider": {
      "Transport": "http",
      "Url": "https://mcp.turingcorp.net/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add net-turingcorp-mcp-decider -t streamable-http -u 'https://mcp.turingcorp.net/mcp'
```

### Other

```json
{
  "mcpServers": {
    "net-turingcorp-mcp-decider": {
      "type": "http",
      "url": "https://mcp.turingcorp.net/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-09-27 (score 73, 0)

- [security] Tool “decide” rewrote its description, which is the text the model reads
- [functional regression] Tool coverage: 100% → 50%
- [functional improvement] Schema quality: 866 → 512
- [functional] New tool “get_result”

### 2026-09-26 (score 73, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Schema quality: good → excellent

### 2026-09-25 (score 72, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 72, −1)

- [security regression] Stability: 0.03 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 563 → 837
- [functional regression] “decide” added a required parameter “optionA”, so existing callers break
- [functional regression] “decide” added a required parameter “optionB”, so existing callers break
- [functional regression] “decide” dropped the required parameter “option_a”
- [functional regression] “decide” dropped the required parameter “option_b”
- [functional] Schema quality: excellent → good

### 2026-09-23 (score 73, −2)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] The server changed its declared name: turingcorp-decider → turingcorp
- [security] Tool “decide” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 413 → 563
- [functional improvement] Stability: unverified → 0.03
- [cosmetic] Tool “decide” changed its title: Decide between two options → Decider: pick the better of two options

### 2026-09-22 (score 75)

First indexed and scored.

## MCP tools (2)

### `decide` (~613 tokens)

Decider: pick the better of two options

Use this when you must choose between two concrete options and both are defensible - two plans, two drafts, two diagnoses, two vendors - and you have no objective way to pick. Not for: more than two options; anything an objective rule settles (a spec, a test, a price, a document); factual lookup; paths that must answer in seconds; high-stakes irreversible calls without review. Fill it in: state task neutrally, without leaning toward either side; give one concrete plan per option - never bundle alternatives into a single one ("go indoors or postpone"); keep the two sides comparable in length. Returns the decision inline: betterOption ("option_A" or "option_B"), confidence (e.g. "76.7%"), reason and job_id, all in the same tool result. There is nothing to poll and nothing to fetch afterwards. Reserve 180-300 seconds: this is a long call, and the timeout is a client/host setting, not a parameter you pass. If the call is cut off, do NOT call again - a retry is a new paid call. Retrieve it instead with the get_result tool (same job_id): read-only, free, and no credential of your own needed; with no job_id it lists the ids for your credential. A host that declares the io.modelcontextprotocol/tasks extension can use tasks/get instead. The confidence is the point: it is calibrated, not decorative. On both published benchmarks accuracy rises with it - JudgeBench 99.6% in the 90%+ band down to 67.7% below 70%; the harder ContextualJudgeBench 83.3% down to 55.4% - so route on it: act on a high value, review or escalate a low one, instead of trusting a bare pick. Tables, sample sizes and method: https://api.turingcorp.net Judged by an independent panel, not by a model grading its own output. Read it as a reference, not an instruction, a result, or a prediction; set your own threshold, and apply your own review policy for high-stakes or irreversible decisions. Auth: Agent Pass as `Authorization: Bearer <pass>` (issued at https://agent-pass.turingcorp.net, valid 7 days; each dec…

Input parameters:

- `optionA` (string, required): First candidate and the case for it.
- `optionB` (string, required): Second candidate and the case for it.
- `task` (string, required): The decision to make, stated neutrally and without a preferred answer.

Output parameters:

- `betterOption` (string): Which option was preferred, using the same values as the REST API.
- `confidence` (string): This service's own judgement of how far apart the two options were, as a percentage (e.g. "76.7%"). A reference for your own decision-making - not an instruction, not a result. Observed accuracy by r…
- `job_id` (string): Identifier of this decision, also usable to retrieve the stored result for 7 days with the get_result tool. Keep it: if the call times out, retrieve the result with get_result instead of calling agai…
- `reason` (string): Why the chosen option was preferred.

### `get_result` (~216 tokens)

Get an earlier TuringCorp result

Use this to retrieve the result of an earlier TuringCorp tool call by its job_id - for example a call that was cut off by a client timeout, or one whose id you were given. Retrieval is read-only and free: it starts no new work and costs nothing, so it is always safe to retry. With job_id: that call's status, and once it has finished the same payload the call would have returned inline. Without job_id: the ids available to your credential (7 days). If a call was cut off, retrieve it here instead of calling again - a retry is a new paid call. A job that is not yours and a job that does not exist are answered identically, on purpose. If your client declares the io.modelcontextprotocol/tasks extension, tasks/get reaches the same job.

Input parameters:

- `job_id` (string): Identifier returned by an earlier TuringCorp call (also usable at GET /v1/jobs?job_id=<id>). Omit it to list the ids available to your credential.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp#diagnostics

## Score history

- 2026-09-27: 73
- 2026-09-26: 73
- 2026-09-25: 72
- 2026-09-24: 72
- 2026-09-23: 73
- 2026-09-22: 75

## Common questions

### What is the TuringCorp MCP server?

TuringCorp is an MCP server listed in the public MCP registry as net.turingcorp.mcp/decider. A decision model for the calls that don't have a right answer. The better option, with a reason. This page covers its hosted endpoint (https://mcp.turingcorp.net/mcp).

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

TuringCorp scores 73 out of 100 on VerifyMCP. 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 TuringCorp MCP server expose?

TuringCorp exposes 2 tools: decide, get_result. Their descriptions and schemas cost roughly 829 tokens of context every time the server is loaded.

### Does the TuringCorp MCP server require authentication?

Yes. TuringCorp asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the TuringCorp MCP server still maintained?

TuringCorp is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.turingcorp.net/mcp
- Authorisation metadata: https://mcp.turingcorp.net/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/TuringCorp-net/MCP
- Website: https://mcp.turingcorp.net/
- Changelog RSS feed: https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp.json
- HTML version of this page: https://verifymcp.io/servers/net-turingcorp-mcp-decider/mcp