TypeSafe AI Jev MCP server
2026년 10월 25일 커밋Jev 결정 모델을 타입화된 도구로 노출하여 라우팅, 분류, 리스크 점수 산출을 위한 구조화된 답변과 보정된 확률을 제공합니다.
다른 이름 devbux/typesafe-mcp
- 스타
- 0
- Tools
- 6
- 다운로드, 30일
- —
- 최신 버전
- —
- 마지막 커밋
- 2026년 10월 25일
- 라이선스
- MIT
TypeSafe AI Jev MCP란?
Jev 결정 모델을 타입화된 도구로 노출하여 라우팅, 분류, 리스크 점수 산출을 위한 구조화된 답변과 보정된 확률을 제공합니다. 6개 도구를 제공합니다. 예: jev_decide, jev_choice, jev_score.
프로젝트 README에서 생성된 요약
TypeSafe AI Jev MCP server 정보
에이전트 워크플로우를 구축하는 개발자는 이 서버를 사용하여 Jev 결정 모델을 통합하고 구조화된 비텍스트 출력을 얻을 수 있습니다. 대화형 텍스트를 생성하는 대신, 도구는 라우팅, 분류, 리스크 점수 산출과 같은 특정 작업에 대해 보정된 확률과 타입화된 답변을 제공합니다. 이는 AI가 문장이 아닌 정밀한 데이터를 반환해야 하는 "대화가 아닌 결정" 단계에 이상적입니다.
서버는 stdio를 통해 로컬에서 실행되며 Claude Desktop, Cursor, VS Code와 같은 MCP 클라이언트와 호환됩니다. TYPESAFE_API_KEY 환경 변수를 통해 제공되는 TypeSafe AI API 키가 필요합니다. 사용자는 npx 또는 bunx를 사용하여 서버를 실행할 수 있습니다. 시스템은 지침을 위한 구조화된 JSON 및 base64로 인코딩된 에셋을 통해 전달되는 이미지를 포함한 복잡한 입력을 지원합니다.
주요 도구로는 한 번의 호출로 여러 질문을 처리하는 jev_decide, 레이블이 지정된 옵션 중에서 선택하는 jev_choice, 순서형 척도를 위한 jev_score, 참/거짓 명제를 위한 jev_noul, 이미지 바운딩 박스를 식별하는 jev_box가 있습니다. 또한 사용 가능한 모델 버전을 확인하기 위한 jev_list_models를 제공합니다.
활용 사례
- 1자동 고객 지원 티켓 라우팅에이전트는 단 한 번의 호출로 티켓을 부서별로 분류하고, 긴급도 점수를 할당하며, 환불 가능성을 예측할 수 있습니다.
프로젝트의 README를 바탕으로 작성되었습니다. 모든 활용 사례는 해당 내용의 인용문과 대조하여 확인합니다.
TypeSafe AI Jev MCP 도구 6
README에서 감지됨jev_decidejev_choicejev_scorejev_nouljev_boxjev_list_models
| jev_decide | — | |
| jev_choice | — | |
| jev_score | — | |
| jev_noul | — | |
| jev_box | — | |
| jev_list_models | — |
구성
TYPESAFE_API_KEY
| 이름 | 설명 | 유형 |
|---|---|---|
| TYPESAFE_API_KEY | — |
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →아직 인증되지 않았습니다. 서버는 80점 이상의 점수, 심각한 결함 없음, 그리고 검사에 충분한 데이터를 갖추어야 합니다. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능devbux/typesafe-mcp is public and reachablegithub.com/devbux/typesafe-mcp ↗통과
- 패키지가 이 저장소를 소스로 명시검사되지 않음
- 빌드 출처(Sigstore 증명)검사되지 않음
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit or release 2026-10-25github.com/devbux/typesafe-mcp ↗통과
- OpenSSF Scorecard검사되지 않음
- 패키지 이름이 인기 패키지와 유사하지 않음검사되지 않음
- 패키지 및 해당 종속성에 중요한 보안 권고 없음검사되지 않음
- 모델에 대한 숨겨진 지침 없음6 tool descriptions and the README read; no override phrases, credential paths or hidden characters통과
- 파괴적인 도구에 라벨 표시됨No tool named like delete, drop or exec통과
- 원격 엔드포인트가 MCP 핸드셰이크에 응답검사되지 않음
README
GitHub에서 보기typesafe-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.
Requirements
- Node.js >= 18 (or Bun) to run the server.
- A TypeSafe AI API key (see Getting an API key).
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_KEYis 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 likecatcould also match insidecategory. - 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: trueheader 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-1.14.0orjev-previewas the model (jev_boxdefaults tojev-1.14.0). A Box answer is always a box, even when the target is absent — pair it with anoulpresence 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):
- Bump the version in
package.json, updateCHANGELOG.md, and push. - Create a GitHub Release for the new version tag (or run the workflow
manually with
workflow_dispatch). - The workflow runs typecheck, tests, and build, then publishes with
npm publish --provenance --access public.
Notes:
- The workflow expects an
NPM_TOKENrepository secret (an npm automation token for an account/organisation that owns the@devbuxscope). - Provenance is enabled (
id-token: writepermission +--provenance), so each published version is linked to its GitHub Actions build. - This is a scoped package (
@devbux/typesafe-mcp);publishConfig.accessis set topublicinpackage.jsonso releases are publicly installable. prepublishOnlyalso runs typecheck, tests, and build for manual publishes.
License
MIT © 2026 devbux
TypeSafe AI Jev MCP 질문
TypeSafe AI Jev MCP는 어떤 도구를 제공하나요?
6개 도구를 제공합니다. 예: jev_decide, jev_choice, jev_score, jev_noul, jev_box.
서버를 실행하려면 무엇이 필요한가요?
Node.js 버전 18 이상(또는 Bun)과 TypeSafe AI API 키가 필요합니다.