# TypeSafe (npm · @foreverworks/mcp-typesafe)

Get calibrated yes or no answers, choices and scores from TypeSafe's Jev, for one item or 1000 rows.

- Trust score: 78/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@foreverworks/mcp-typesafe`: 78/100 (this document), [markdown](https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe.md), [page](https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe)

## Channel facts

- Registry: `npm`
- Package: `@foreverworks/mcp-typesafe`
- Version: `0.1.2`
- 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 2026-11-05.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 7 of 24 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to foreverworks/mcps).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1104 tokens (~368/item across 3 items; 3 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 not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 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 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 TypeSafe MCP server?

TypeSafe runs locally as an npm package, launched with npx -y @foreverworks/mcp-typesafe. 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 com-foreverworks-typesafe -- npx -y @foreverworks/mcp-typesafe
```

### Cursor

```json
{
  "mcpServers": {
    "com-foreverworks-typesafe": {
      "command": "npx",
      "args": [
        "-y",
        "@foreverworks/mcp-typesafe"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-foreverworks-typesafe": {
      "command": "npx",
      "args": [
        "-y",
        "@foreverworks/mcp-typesafe"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-foreverworks-typesafe -- npx -y @foreverworks/mcp-typesafe
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-foreverworks-typesafe --command npx --arg -y --arg @foreverworks/mcp-typesafe
```

### Hermes

```yaml
mcp_servers:
  com-foreverworks-typesafe:
    command: "npx"
    args: ["-y", "@foreverworks/mcp-typesafe"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-foreverworks-typesafe": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@foreverworks/mcp-typesafe"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-foreverworks-typesafe -t stdio -c npx -a -y @foreverworks/mcp-typesafe
```

### Other

```json
{
  "mcpServers": {
    "com-foreverworks-typesafe": {
      "command": "npx",
      "args": [
        "-y",
        "@foreverworks/mcp-typesafe"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 78, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.89

### 2026-11-03 (score 67)

First indexed and scored.

## MCP tools (3)

### `ask` (~241 tokens)

Ask Jev

Ask TypeSafe's Jev, a System One model, typed questions about one state and get calibrated answers: a `noul` is the probability that a yes/no statement holds, a `choice` picks one of your options with a probability each, a `score` places the state on your ordered levels. Jev writes no text and does no multi-step reasoning: use it for fast, narrow judgments (routing, triage, relevance, a policy check) whose probabilities you then threshold. One narrow judgment per question; a no-match option where nothing may fit. A probability near 0.5 means undecided, not medium. About 0.5 s a call.

Input parameters:

- `model` (string): A model from health. Default: the server's, jev-latest.
- `questions` (object, required): Your question id -> question. Every independent judgment about the same state goes in one call: they run together and cannot see each other.
- `state` (required): What is judged: text, or JSON with named fields (a record, a thread, a posting with its metadata) the questions can point at, e.g. `posting.location`.

### `ask_batch` (~745 tokens)

Ask Jev over many states

The same questions over up to 1000 states, several requests at a time: triage postings, transactions, emails or passages without reading them all yourself. Replies with a summary per question (choice: counts; noul: mean and how many are >= 0.7 and <= 0.3; score: mean, min, max) and each row's compact answers (a noul's probability, a choice's pick and confidence, a score and its confidence). For a large batch pass list 'none' or 'failed' with save true: every row's full answers go to a JSONL file in the outbox and the reply names it with its sha256 and size. A row that fails is reported and the rest go on. Rows already in a file go as items_file, not typed into items: that keeps them out of your context and exactly as written. thresholds turn each answer into act, review or abstain; where lists only the rows that meet conditions, top only the k highest by a question, and counts tallies the answers (and verdicts) of the rows where keeps: over a large batch they keep the reply to the rows that matter. A client that asks for progress hears the rows done; cancelling stops the rows not yet asked.

Input parameters:

- `concurrency` (integer): Requests in flight at once.
- `counts` (boolean): Also tally each question's answers (a noul's yes/no/between, a choice's picks, a score's nearest levels) and verdicts over the rows where keeps.
- `items` (array): The rows, typed into the call. Give items or items_file.
- `items_file` (object): The rows as a UTF-8 file instead of items: JSONL, one {"id", "state"} object per line, or one JSON array of them; at most 1000, every row with an id above 20. The reply names its sha256 and size. Nev…
- `list` (string): Which rows the reply lists; the summary always covers every row.
- `model` (string): A model from health. Default: the server's, jev-latest.
- `probabilities` (boolean): Also list each row's full distribution per choice and score.
- `questions` (object, required): Your question id -> question. Every independent judgment about the same state goes in one call: they run together and cannot see each other.
- `save` (boolean): Also write every row's full answers to the outbox as JSONL.
- `thresholds` (object): Question id -> thresholds: each row's answer to that question gets a verdict, act, review or abstain, taken on its certainty (a noul's |p - 0.5| x 2, a choice's or a score's confidence, rounded down…
- `top` (object): Only the k rows (of those where keeps) with the highest value for one question, highest first.
- `where` (object): Question id -> condition; the reply lists only the answered rows meeting every one, and says how many matched. E.g. {"urgent": true, "team": ["billing"], "mood": {"min": 1.5}}. Checked against the qu…

### `health` (~36 tokens)

Health

Check that the TypeSafe API key is present and accepted, and list the models it can use. Run this before concluding the MCP is broken.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe#diagnostics

## Score history

- 2026-11-05: 78
- 2026-11-04: 78
- 2026-11-03: 67

## Common questions

### What is the TypeSafe MCP server?

TypeSafe is an MCP server listed in the public MCP registry as com.foreverworks/typesafe. Get calibrated yes or no answers, choices and scores from TypeSafe's Jev, for one item or 1000 rows. This page covers its npm package (@foreverworks/mcp-typesafe).

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

TypeSafe scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 TypeSafe MCP server expose?

TypeSafe exposes 3 tools: ask, ask_batch, health. Their descriptions and schemas cost roughly 1,022 tokens of context every time the server is loaded.

### Is the TypeSafe MCP server still maintained?

TypeSafe is still listed as active in the MCP registry. We last reached this channel on 5 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 TypeSafe MCP server under?

TypeSafe 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

- npm package: https://www.npmjs.com/package/@foreverworks/mcp-typesafe
- Socket report: https://socket.dev/npm/package/@foreverworks/mcp-typesafe
- Repository: https://github.com/foreverworks/mcps
- Website: https://foreverworks.github.io/mcps/servers/typesafe/
- Changelog RSS feed: https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe.json
- HTML version of this page: https://verifymcp.io/servers/com-foreverworks-typesafe/foreverworks-mcp-typesafe