# Arbitype (pypi · arbitype)

Typed decision tools for AI agents, powered by TypeSafe Jev.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-23

## Components

- pypi · `arbitype`: 66/100 (this document), [markdown](https://verifymcp.io/servers/renwang-huang-arbitype/arbitype.md), [page](https://verifymcp.io/servers/renwang-huang-arbitype/arbitype)

## Channel facts

- Registry: `pypi`
- Package: `arbitype`
- Version: `0.7.0`
- 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 2026-09-23.

- **Supply Chain Security**: 94/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs a script at install time (build_backend,cmdclass) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.
  - 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 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 70/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 879 tokens (~97/item across 9 items; 9 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**: 74/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 8% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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).

**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 Arbitype MCP server?

Arbitype runs locally as a PyPI package, launched with uvx arbitype. 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 renwang-huang-arbitype -- uvx arbitype
```

### Cursor

```json
{
  "mcpServers": {
    "renwang-huang-arbitype": {
      "command": "uvx",
      "args": [
        "arbitype"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "renwang-huang-arbitype": {
      "command": "uvx",
      "args": [
        "arbitype"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add renwang-huang-arbitype -- uvx arbitype
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "renwang-huang-arbitype": {
      "type": "local",
      "command": [
        "uvx",
        "arbitype"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add renwang-huang-arbitype --command uvx --arg arbitype
```

### Hermes

```yaml
mcp_servers:
  renwang-huang-arbitype:
    command: "uvx"
    args: ["arbitype"]
```

### Netclaw

```json
{
  "McpServers": {
    "renwang-huang-arbitype": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "arbitype"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add renwang-huang-arbitype -t stdio -c uvx -a arbitype
```

### Other

```json
{
  "mcpServers": {
    "renwang-huang-arbitype": {
      "command": "uvx",
      "args": [
        "arbitype"
      ]
    }
  }
}
```

## 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.

### 2026-09-22 (score 66)

First indexed and scored.

## MCP tools (9)

### `evaluate` (~92 tokens)

USE WHEN you need raw typed Jev answers for one or more bounded noul, choice, or score questions. DO NOT USE WHEN you need prose, code generation, arithmetic, dates, or a specialized primitive such as route or gate.

Input parameters:

- `model` (string): Optional model id or alias.
- `questions` (object, required): Map of question id to a TypeSafe question.
- `state` (required): Text or structured evidence.

Output parameters:

- `answers` (object)
- `model` (string)
- `usage` (object)

### `classify` (~77 tokens)

USE WHEN you need exactly one label from a closed, unordered set and its probability distribution. DO NOT USE WHEN labels are ordered levels (use score), options are next actions (use route), or inputs are claims (use verify).

Input parameters:

- `instructions` (required)
- `labels` (object, required)
- `model` (string)
- `state` (required)

Output parameters:

- `answer` (object)
- `evaluation` (object)
- `model` (string)
- `type`
- `usage` (object)

### `score` (~72 tokens)

USE WHEN you need a weighted rating over two or more ordered rubric levels. DO NOT USE WHEN choices are unordered categories (use classify), next actions (use route), or thresholded checks (use gate).

Input parameters:

- `instructions` (required)
- `levels` (array, required)
- `model` (string)
- `state` (required)

Output parameters:

- `answer` (object)
- `evaluation` (object)
- `model` (string)
- `type`
- `usage` (object)

### `check` (~86 tokens)

USE WHEN you need one bounded yes/no proposition and its probability. DO NOT USE WHEN you need to verify multiple named claims (use verify), combine checks with thresholds (use gate), or assess an entire object or review package (use review).

Input parameters:

- `false_criteria`
- `instructions` (required)
- `model` (string)
- `state` (required)
- `true_criteria`

Output parameters:

- `answer` (object)
- `evaluation` (object)
- `model` (string)
- `type`
- `usage` (object)

### `verify` (~97 tokens)

USE WHEN you need to check multiple named claims against supplied evidence in one request. DO NOT USE WHEN you need one proposition (use check), an overall quality/risk review (use review), or a pass/review/fail threshold (use gate). Results are signals, not proof.

Input parameters:

- `claims` (object, required)
- `false_criteria`
- `model` (string)
- `state` (required)
- `true_criteria`

Output parameters:

- `answers` (object)
- `evaluation` (object)
- `type`

### `gate` (~96 tokens)

USE WHEN you need to combine multiple bounded checks and thresholds into pass/review/fail. DO NOT USE WHEN you need claim-by-claim evidence checking (use verify) or whole-object quality/risk assessment (use review). This is not authorization or a security boundary.

Input parameters:

- `checks` (object, required)
- `model` (string)
- `pass_at` (number)
- `review_at` (number)
- `state` (required)

Output parameters:

- `checks` (object)
- `decision`
- `evaluation` (object)
- `policy` (object)
- `type`

### `route` (~81 tokens)

USE WHEN you need exactly one next action from a closed set of actions. DO NOT USE WHEN you need a topic/category label (use classify), an ordered rating (use score), or action execution. This suggests an action; it never executes it.

Input parameters:

- `actions` (object, required)
- `instructions`
- `model` (string)
- `state` (required)

Output parameters:

- `answer` (object)
- `evaluation` (object)
- `model` (string)
- `route` (string)
- `type`
- `usage` (object)

### `review` (~111 tokens)

USE WHEN you need an overall quality or risk review of a whole-object artifact such as a diff, plan, release, or test report against multiple checks. DO NOT USE WHEN you need claim-by-claim verification (use verify), a single proposition (use check), or next-action selection (use route). It returns signals and never edits files.

Input parameters:

- `checks` (object, required)
- `model` (string)
- `pass_at` (number)
- `review_at` (number)
- `state` (required)

Output parameters:

- `checks` (object)
- `decision`
- `evaluation` (object)
- `policy` (object)
- `type`

### `health` (~59 tokens)

USE WHEN you need local Arbitype configuration or an explicitly requested live provider check. DO NOT USE WHEN you need a business decision; health does not evaluate state and does not make a network request unless live=true is explicit.

Input parameters:

- `live` (boolean)

Output parameters:

- `api_key_configured` (boolean)
- `base_url` (string)
- `live` (boolean)
- `max_retries` (integer)
- `model` (string)
- `server` (string)
- `status` (string)
- `timeout_seconds` (number)
- `type`
- `version` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/renwang-huang-arbitype/arbitype#diagnostics

## Score history

- 2026-09-23: 66
- 2026-09-22: 66

## Common questions

### What is the Arbitype MCP server?

Arbitype is an MCP server listed in the public MCP registry as io.github.Renwang-Huang/arbitype. Typed decision tools for AI agents, powered by TypeSafe Jev. This page covers its PyPI package (arbitype).

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

Arbitype scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 September 2026. 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 Arbitype MCP server expose?

Arbitype exposes 9 tools: evaluate, classify, score, check, verify, and 4 more. Their descriptions and schemas cost roughly 771 tokens of context every time the server is loaded.

### Is the Arbitype MCP server still maintained?

Arbitype is still listed as active in the MCP registry. We last reached this channel on 23 September 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 Arbitype MCP server under?

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

## Links

- PyPI project: https://pypi.org/project/arbitype/
- Socket report: https://socket.dev/pypi/package/arbitype
- Repository: https://github.com/Renwang-Huang/arbitype
- Changelog RSS feed: https://verifymcp.io/servers/renwang-huang-arbitype/arbitype.xml
- Changelog JSON feed: https://verifymcp.io/servers/renwang-huang-arbitype/arbitype.json
- HTML version of this page: https://verifymcp.io/servers/renwang-huang-arbitype/arbitype