Skip to main content
Glama

typesafe-mcp

A standard Model Context Protocol (MCP) server that exposes TypeSafe AI's Jev decision model as typed tools — publishable to npm and runnable anywhere with npx or bunx.

npx -y @devbux/typesafe-mcp

What is Jev?

Jev is TypeSafe AI's System One decision model. It never generates prose. Instead, you give it:

  • a state — a situation described as text or structured JSON, and

  • a set of typed questions about that state,

and Jev returns typed answers with calibrated probabilities:

Question type

You define

Jev returns

choice

2–255 labelled options (each with an optional description)

the chosen option, a confidence value, and a probability for every option

score

an ordered scale of level descriptions (at least 2)

a numeric score on your scale, confidence, and per-level probabilities

noul

a proposition (optionally with true/false descriptions)

a calibrated probability (0..1) that the proposition is true

box

what to find, and in which image

the target's bounding-box edges (top, bottom, left, right as fractions 0..1) and a confidence value

Questions can also read images: pass pictures in an assets map and reference them from the state, instructions, or criteria — see Images. instructions and criteria accept structured JSON (objects/arrays), not just strings.

Because the output is structured and calibrated rather than free text, Jev is well suited to routing, triage, moderation, risk scoring, prioritisation, and any other "decide, don't chat" step inside an agent workflow.

Related MCP server: jev-mcp

Requirements

Install & run

The server speaks MCP over stdio, so you normally don't run it by hand — your MCP client launches it. The commands below are how clients (or you, for a quick smoke test) start it.

npx (Node)

TYPESAFE_API_KEY=your-key npx -y @devbux/typesafe-mcp

bunx (Bun)

TYPESAFE_API_KEY=your-key bunx @devbux/typesafe-mcp

Global install (npm)

npm install -g @devbux/typesafe-mcp
TYPESAFE_API_KEY=your-key typesafe-mcp

Global install (Bun)

bun add -g @devbux/typesafe-mcp
TYPESAFE_API_KEY=your-key typesafe-mcp

The server starts even when TYPESAFE_API_KEY is not set, so clients can still list its tools; each tool call then returns a clear error naming the missing variable instead of crashing.

Getting an API key

Create an API key in the TypeSafe console at typesafe.ai, then expose it to the server as the TYPESAFE_API_KEY environment variable. Never commit your key to source control.

MCP client configuration

Generic (mcpServers JSON)

Most MCP clients (Claude Desktop, and many others) accept a configuration like this — see also examples/mcp-config.json:

{
  "mcpServers": {
    "typesafe": {
      "command": "npx",
      "args": ["-y", "@devbux/typesafe-mcp"],
      "env": {
        "TYPESAFE_API_KEY": "YOUR_TYPESAFE_API_KEY"
      }
    }
  }
}

Using Bun instead:

{
  "mcpServers": {
    "typesafe": {
      "command": "bunx",
      "args": ["@devbux/typesafe-mcp"],
      "env": {
        "TYPESAFE_API_KEY": "YOUR_TYPESAFE_API_KEY"
      }
    }
  }
}

Claude Code

claude mcp add typesafe \
  -e TYPESAFE_API_KEY=YOUR_TYPESAFE_API_KEY \
  -- npx -y @devbux/typesafe-mcp

Cursor / VS Code

Cursor and VS Code use the same mcpServers JSON shape above (Cursor: .cursor/mcp.json or Settings → MCP; VS Code: .vscode/mcp.json uses a top-level "servers" key with the same per-server fields). Paste the generic config and replace the placeholder key.

Configuration

Environment variable

Default

Description

TYPESAFE_API_KEY

(unset)

Bearer API key for the TypeSafe AI API. Required for tool calls; the server still starts without it.

TYPESAFE_BASE_URL

https://api.typesafe.ai

Base URL of the TypeSafe AI API.

TYPESAFE_JEV_MODEL

jev-latest

Jev model id to request. Can be overridden per call with the tools' optional model argument. Use jev_list_models to see what is available.

Tools

All tools return the Jev API response as JSON text content. Errors (missing API key, HTTP 401/403/429/5xx, network failures, timeouts) are returned as MCP tool errors (isError) with a clear message that includes the HTTP status — never your API key.

Tool

Inputs

Output

jev_decide

state (string | JSON object | JSON array), questions (map of name → typed question, at least 1), optional model, assets, long_context

All answers in one call: { answers, model, usage }

jev_choice

state, instructions, options (object: label → description or null, 2–255), optional model, assets, long_context

One Choice answer under the name answer

jev_score

state, instructions, levels (array of level descriptions, at least 2, ordered low → high), optional model, assets, long_context

One Score answer under the name answer

jev_noul

state, instructions, optional criteria ({ "true": ..., "false": ... } descriptions), optional model, assets, long_context

One Noul answer (probability 0..1) under the name answer

jev_box

state, instructions (what to find, and in which image), optional assets, model (default jev-1.14.0), long_context

One Box answer (box edges + confidence) under the name answer

jev_list_models

(none)

{ models: [{ name, description, release_date }] }

assets and long_context are described under Images and Long context.

Question shapes for jev_decide

{
  "type": "choice",
  "instructions": "Which department should handle this?",
  "criteria": { "billing": "Payments and invoices", "technical": null }
}
{
  "type": "score",
  "instructions": "How urgent is this?",
  "criteria": ["not urgent", "low", "medium", "high", "critical"]
}
{
  "type": "noul",
  "instructions": "Is a refund likely to be requested?"
  // "criteria" is optional for noul and omitted when not provided
}
{
  "type": "box",
  "instructions": "the coffee mug in `kitchen_photo`"
  // box takes no criteria; it needs an image in the request and Jev 1.14
}

Images

An image can go anywhere text can go in a request: in the state, in a question's instructions, and in its criteria. Every decision tool accepts an optional assets argument — a map from a reference string to an image, base64-encoded:

{
  "state": "Doorbell camera frame: doorbell_img",
  "questions": {
    "person_at_door": {
      "type": "noul",
      "instructions": "Is a person visible in doorbell_img?"
    },
    "person_where": {
      "type": "box",
      "instructions": "the person in `doorbell_img`"
    }
  },
  "assets": {
    "doorbell_img": { "data_base64": "<base64, no data: prefix>", "format": "jpg" }
  },
  "model": "jev-1.14.0"
}

Rules from the TypeSafe docs:

  • Write each asset's reference wherever the image belongs (whole value or inside a longer string). Every asset must be referenced at least once, or the API returns 400 — this server checks that before sending. Use distinctive references (a UUID is safest): references match as plain text, so a short one like cat could also match inside category.

  • Formats: PNG or JPEG only, still images. Each image: at most 16 MiB, each side 280–1568 px; the request body and all images together are capped at 32 MiB. Images are never resized by the API — prepare them (upright, within the limits) before sending.

  • Images are an opt-in "danger zone" feature: the server automatically sends the TypeSafe-Danger-Zone-Images: true header whenever a request has assets or a Box question. TypeSafe marks these features experimental — formats and limits may change between releases.

  • Jev 1.13 and 1.14 both accept images. Box questions need Jev 1.14: send jev-1.14.0 or jev-preview as the model (jev_box defaults to jev-1.14.0). A Box answer is always a box, even when the target is absent — pair it with a noul presence check when that matters.

  • The API also accepts multipart uploads; MCP tool calls carry JSON, so this server always uses the base64 form.

Long context

Jev's default context limits are 64k tokens per request and 32k per question. Any decision tool accepts long_context: true, which sends the TypeSafe-Danger-Zone-Long-Context: true header and raises both limits to 262k tokens. TypeSafe marks this experimental too: it is slower and less accurate, so use it only when a request does not fit the default limits.

Worked example

A support ticket comes in. In one jev_decide call you can route it, rate its urgency, and estimate refund risk:

Request (tool jev_decide):

{
  "state": "Customer writes: 'I was charged twice for my subscription this month and I want my money back today. This is the second billing problem in three months.'",
  "questions": {
    "department": {
      "type": "choice",
      "instructions": "Which department should handle this ticket?",
      "criteria": {
        "billing": "Charges, invoices, payments and refunds",
        "technical": "Product bugs and technical problems",
        "sales": "Pricing, plans and new purchases"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "How urgent is this ticket?",
      "criteria": ["not urgent", "low", "medium", "high", "critical"]
    },
    "refund_likely": {
      "type": "noul",
      "instructions": "Is this customer likely to request a refund?"
    }
  }
}

Response (shape; exact values come from the live model):

{
  "answers": {
    "department": {
      "type": "choice",
      "choice": "billing",
      "confidence": 0.91,
      "probabilities": { "billing": 0.91, "technical": 0.06, "sales": 0.03 }
    },
    "urgency": {
      "type": "score",
      "score": 4,
      "confidence": 0.8,
      "probabilities": { "1": 0.02, "2": 0.05, "3": 0.13, "4": 0.55, "5": 0.25 }
    },
    "refund_likely": {
      "type": "noul",
      "noul": 0.72
    }
  },
  "model": "jev-1.13.0",
  "usage": { "input_tokens": 120, "output_tokens": 45 }
}

Development

git clone https://github.com/devbux/typesafe-mcp.git
cd typesafe-mcp

npm install
npm run dev        # run the server from source with tsx (stdio)
npm run typecheck  # tsc --noEmit
npm test           # vitest (fake fetch — no live network calls)
npm run build      # bundle to dist/index.js with tsup
npm start          # run the built server

Project layout:

src/
  index.ts       stdio bootstrap
  server.ts      MCP server + the six jev_* tools (zod-validated)
  config.ts      environment parsing (TYPESAFE_*)
  jev/
    client.ts    typed JevClient for POST /v1/systemone and GET /v1/models
    types.ts     request/response types for the Jev API
test/
  client.test.ts JevClient + config unit tests

Publishing

Releases are published to npm by the Publish to npm GitHub Action (.github/workflows/publish.yml):

  1. Bump the version in package.json, update CHANGELOG.md, and push.

  2. Create a GitHub Release for the new version tag (or run the workflow manually with workflow_dispatch).

  3. The workflow runs typecheck, tests, and build, then publishes with npm publish --provenance --access public.

Notes:

  • The workflow expects an NPM_TOKEN repository secret (an npm automation token for an account/organisation that owns the @devbux scope).

  • Provenance is enabled (id-token: write permission + --provenance), so each published version is linked to its GitHub Actions build.

  • This is a scoped package (@devbux/typesafe-mcp); publishConfig.access is set to public in package.json so releases are publicly installable.

  • prepublishOnly also runs typecheck, tests, and build for manual publishes.

License

MIT © 2026 devbux

Available Tools

6 tools
jev_boxJev: box question (find where something is in an image)A

Ask Jev a single Box question: locate one target in an image. Returns the box edges as fractions of the image size (top, bottom, left, right, each 0..1) plus a confidence value, under the question name "answer". The image must be in the request: reference it from the state or the instructions and pass it in assets. Box needs Jev 1.14, so this tool sends jev-1.14.0 unless you pass another model (jev-preview also works). A Box answer is always a box, even when the target is absent; pair it with jev_noul when you need a presence check.

Inputs: state (required), instructions (required), model, assets, +1 more.

jev_choiceJev: choice questionA

Ask Jev a single Choice question: pick exactly one option from a labelled set. Returns the chosen option, a confidence value, and calibrated probabilities for every option. The answer is returned under the question name "answer".

Inputs: state (required), options (required), instructions (required), model, +2 more.

jev_decideJev: decide (multiple typed questions)A

Ask TypeSafe AI's Jev decision model one or more typed questions (choice, score, noul and/or box) about a state in a single call. Returns typed answers with calibrated probabilities. The state may be text or structured JSON. Images: pass them in assets and write each image's reference in the state, instructions, or criteria where it belongs.

Inputs: state (required), questions (required), model, assets, +1 more.

jev_list_modelsJev: list modelsA

List the TypeSafe AI models available to the configured API key (name, description, release date).

Inputs: no named parameters.

jev_noulJev: noul questionA

Ask Jev a single Noul question: estimate the probability (0..1) that a proposition about the state is true. Returns the calibrated probability under the question name "answer".

Inputs: state (required), instructions (required), model, assets, +2 more.

jev_scoreJev: score questionA

Ask Jev a single Score question: rate the state on an ordered scale you define. Returns a numeric score, a confidence value, and probabilities per level. The answer is returned under the question name "answer".

Inputs: state (required), levels (required), instructions (required), model, +2 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation4/5

    The four question-type tools (choice, score, noul, box) each map to a distinct answer type, and the box description explicitly directs users to pair it with noul for presence checks. The only overlap is jev_decide, which bundles the same question types in a batch call; the descriptions clarify this, but an agent could still reasonably default to jev_decide for everything, blurring the boundary.

    Naming Consistency4/5

    All tools share a consistent 'jev_' prefix and snake_case, so the set reads predictably. Minor deviation: jev_list_models is verb_noun while jev_choice/score/noul/box are bare nouns naming question types, with jev_decide as a verb — mostly cosmetic.

    Tool Count5/5

    Six tools is well-scoped for a decision-model API: one per question type, a batch aggregator, and a model lister. No tool feels redundant or missing at this size.

    Completeness4/5

    The surface covers all four documented answer types plus batching and model discovery, which is the core of the domain. Minor gaps remain — no per-model capability introspection, usage/credit reporting, or error/diagnostic helper — but core workflows are covered.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables coding or reasoning agents to request structured judgments from TypeSafe's Jev model at decision points, including choices, scores, claim verification, and code reviews, with probabilities and confidence returned as data.
      5
      13 npm
      MIT
    • A
      license
      B
      quality
      C
      maintenance
      Enables AI agents to obtain typed judgments from TypeSafe's Jev System One models, including yes/no probabilities, multiple-choice selections with distributions, and rubric-based scores, directly usable in code.
      5
      2
      AGPL 3.0
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents to offload yes/no, multiple-choice, and scoring questions to TypeSafe's Jev, returning compact confidence-scored answers to save tokens and improve speed.
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables agents to query the TypeSafe Jev decision model for typed answers—yes/no, choice, and score questions—with calibrated probabilities, batched in a single request under a local context-budget guard.
      6
      MIT