OpenJEV MCP Server

Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.

Local serverstdio

What is the OpenJEV MCP Server?

OpenJEV is an MCP integration. Typed AI judgments for agents: choice, score, and yes/no probabilities instead of prose.

Packages and local setup

The published npm package is openjev-mcp, version 0.2.0. Its declared MCP transport is stdio.

The package declares OPENJEV_API_KEY (required): OpenJEV API key from https://openjev.sh/dashboard; OPENJEV_MODEL: Model alias used when a call does not name one (default: openjev); OPENJEV_TIMEOUT_MS: Per-attempt timeout in milliseconds, 1000-600000 (default: 30000); OPENJEV_MAX_RETRIES: Retries after the first attempt, 0-10 (default: 2); OPENJEV_BATCH_CONCURRENCY: Requests one jev_batch call keeps in flight at once, 1-16 (default: 4).

Before connecting

Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.

Project and source

View the publisher’s registry entry · Project repository. This profile uses version 0.2.0 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.

Browse related other integrations MCP servers for tools that cover the same kind of work.

Configuration

VariableDescriptionRequired
OPENJEV_API_KEYOpenJEV API key from https://openjev.sh/dashboardYes
OPENJEV_MODELModel alias used when a call does not name one (default: openjev)Check documentation
OPENJEV_TIMEOUT_MSPer-attempt timeout in milliseconds, 1000-600000 (default: 30000)Check documentation
OPENJEV_MAX_RETRIESRetries after the first attempt, 0-10 (default: 2)Check documentation
OPENJEV_BATCH_CONCURRENCYRequests one jev_batch call keeps in flight at once, 1-16 (default: 4)Check documentation