TypeSafe's Jev model for typed decisions — ask yes/no, multiple-choice or rubric-score questions about a block of state and get calibrated probabilities back instead of prose. Built for classification, routing and scoring steps inside a workflow
OpenClaw is a self-hosted agent gateway. It connects to remote MCP servers over streamable HTTP, configured in one file.
This guide connects Jev to OpenClaw through MewCP, so OpenClaw can use Jev's 2 tools, like evaluate_state and list_models, without your Jev credentials ever reaching the app.
Your Jev API key is stored encrypted and injected only at call time. Your agent never holds it, so it can never leak it, log it or paste it into a prompt.
More apps
Turn your AI agent into a creative studio The world's best image, video, audio and 3D models, inside the AI assistant you already use.
Access Google's Gemini models for text generation, reasoning, coding, multimodal analysis and AI-powered workflows. Process text, images and structured data through advanced AI capabilities.
The Fish Audio MCP server gives AI agents direct access to your Fish Audio account: they can browse the voice library, clone a voice, generate speech, transcribe audio, generate or edit images and videos, and produce multi-speaker Story Studio projects for you.
ElevenLabs enables AI agents to create, configure, and manage conversational voice agents, inspect conversation transcripts, manage knowledge bases and tools, run evaluations, review support tickets, estimate usage costs, and generate speech audio from text.
Other clients
Jev works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Jev tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
Edit ~/.openclaw/openclaw.json. Create it if it doesn't exist.
Restart OpenClaw. Sign in when the browser window opens.
Start a new chat and ask: "List the tools you can use from MewCP." You should see your connected apps.
Evaluates the given state against a map of typed questions and returns one structured answer per question, keyed by the same ids used in the request. Every question is evaluated independently and in parallel against the same state, and noul (yes/no), choice (single-select), and score (rubric) questions can be freely mixed within a single call.
Lists the model names and aliases this account can pass in the evaluate-state `model` field, with a description and release date for each. This list currently only surfaces aliases such as `jev-latest` and `jev-preview` — a versioned model ID (e.g. `jev-1.13.0`) is still accepted by the evaluate-state `model` field even when it does not appear here.
