Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@typesafe-mcp Evaluate 'Package missing, please reship.' Is the customer requesting a replacement?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
typesafe-mcpMCP server for TypeSafe's Jev model
typesafe-mcp exposes a single evaluate tool that sends evidence and
questions to TypeSafe and returns structured answers and
probabilities.
It is written in JavaScript and uses the MCP SDK and Zod. No build step is required.
Requires Node.js 22 or later. From the project directory:
npm ciSet TYPESAFE_API_KEY in the environment used to start the server. Keys are
available from the TypeSafe console.
Related MCP server: Jev MCP Proxy
For Codex, add the following to your MCP configuration, replacing the path with this checkout's absolute path:
[mcp_servers.typesafe]
command = "node"
args = ["/absolute/path/typesafe-mcp/server.js"]
env_vars = ["TYPESAFE_API_KEY"]Other MCP clients can launch node /absolute/path/typesafe-mcp/server.js using
the same environment variable. The server communicates via stdin/stdout.
Call evaluate with the evidence in state and a map of named questions:
{
"state": "My order arrived damaged. Please issue a refund.",
"questions": {
"refund_requested": {
"type": "noul",
"instructions": "Does the customer request a refund?"
}
}
}Type | Criteria | Answer |
| Optional descriptions of | Probability that the condition holds |
| Map of option names to descriptions or | Selected option, probabilities, and confidence |
| Ordered array of level descriptions | Weighted score, probabilities, and confidence |
Batch independent questions for the same state in one call. model defaults to
jev-latest. State, instructions, and rubric descriptions can include
structured JSON. Encode large integer identifiers as strings to preserve their
digits.
See the TypeSafe API reference for details on question and answer formats. The provided evidence is sent to TypeSafe, and standard API charges apply.
The API response includes the answers and token usage. Questions are validated before sending; missing or mismatched answer types trigger MCP tool errors. Answer values and probability distributions pass through without further validation or automatic accept/reject decisions.
Requests have a 60-second deadline and honour MCP cancellation. HTTP errors report the status without echoing the upstream body. Failed requests are not retried.
npm testTests cover the MCP interface and request handling using mock responses. They require no API key or paid calls.
To test the real API, add your local testing key to the gitignored .env file
as TYPESAFE_API_KEY, then run:
npm run test:liveThe live test sends a single batch of synthetic evidence through the MCP server,
covering all three question types. It verifies response formats, ranges, and
allowed choices rather than exact probabilities. It incurs standard API charges
and is excluded from npm test.
Licensed under the MIT licence.
This server cannot be deployed
Calibrated judgments for text: yes/no probabilities, picks from your options, or scores.
Reproducible benchmarks and reliability evidence for agent tools.
Jev-powered decisions, web search, PDF/web to Markdown, summarize. From $0.001, no API key.
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
