Atlas / MCP servers / rashedint32 / jev-mcp

jev-mcpSAFE

Name: jev-mcp
Author: rashedint32

mcp/rashedint32/jev-mcp

MCP server by rashedint32 · ai agents · classification · claude code · Audited 2026-10-10

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

7 7r · 0w · 0d

Transport

stdio

License

MIT

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://www.npmjs.com/package/jev-mcp) [](https://www.npmjs.com/package/jev-mcp)

An MCP server that exposes TypeSafe Jev as typed judgment tools.

Jev is a System One model. It returns a typed answer and a calibrated probability distribution, never prose. These tools surface that faithfully rather than hiding it behind a label.

Install

Requires Node 20.12+ and a TypeSafe API key from console.typesafe.ai.

Claude Code plugin

One marketplace add, one install. This registers the server and the agent skill together, so there is no separate skill step.

/plugin marketplace add rashedInt32/jev-mcp
/plugin install jev@jev-mcp

The plugin runs the published package through npx -y jev-mcp@, so nothing needs building. The first launch downloads the package, so allow a few seconds before the server shows as connected in claude mcp list.

Any MCP client

claude mcp add --scope user jev -- npx -y jev-mcp

Or in a client's JSON config:

{
"mcpServers": {
"jev": { "command": "npx", "args": ["-y", "jev-mcp"] }
}
}

Do not register the server directly and install the plugin. Two servers named jev will otherwise both register.

The key

The server reads the key from TYPESAFE_API_KEY in its environment, then from JEV_API_KEY, then from ~/.config/typesafe/key. It is never a tool argument, so it cannot land in a transcript or in a model's context.

The key file is the most reliable source, because some MCP clients strip the environment before spawning servers:

mkdir -p ~/.config/typesafe
printf '%s' "ts_..." > ~/.config/typesafe/key
chmod 600 ~/.config/typesafe/key

If you prefer the variable, put it in ~/.zshenv rather than in an

Read from source at commit 6ead2f5b4f47OBSERVED · 2026-10-10

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.

claude-code

claude mcp add jev-mcp --env JEV_API_KEY=${JEV_API_KEY} --env JEV_KEY_FILE=${JEV_KEY_FILE} --env TYPESAFE_API_KEY=${TYPESAFE_API_KEY} -- npx -y [email protected]

claude-desktop

{
  "mcpServers": {
    "jev-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "JEV_API_KEY": "${JEV_API_KEY}",
        "JEV_KEY_FILE": "${JEV_KEY_FILE}",
        "TYPESAFE_API_KEY": "${TYPESAFE_API_KEY}"
      }
    }
  }
}

Exposed tools (7)

7 read · 0 write · 0 destructive.

Tool	Risk	Description
`jev-latest`	read	Flagship
`jev_ask`	read
`jev_check`	read
`jev_classify`	read
`jev_models`	read
`jev_score`	read
`jev_triage`	read

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: none-observed
Network: none-observed
Shell: none-observed
Dependencies: not all pinned
Secrets in source: none-found