OpenJEV MCP
An MCP server that converts natural language queries into typed, structured decisions with calibrated probabilities. It supports classification, routing, scoring, and flagging tasks, allowing agents to branch logic based on precise outputs rather than prose. It handles validation, retries, and batch processing for efficient agent workflows.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 1 GitHub star
What you can do with it
- Support triage and ticket routing
- Content moderation and harm scoring
- Agent routing and workflow selection
- LLM-as-judge evaluation
Source and maintenance
- Last repository push
- Latest release
- v0.2.0
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
openjev-mcp 0.2.0
{
"version": "0.2.0",
"transport": "stdio",
"identifier": "openjev-mcp",
"registryType": "npm",
"environmentVariables": [
{
"name": "OPENJEV_API_KEY",
"format": "string",
"isRequired": true,
"description": "OpenJEV API key from https://openjev.sh/dashboard"
},
{
"name": "OPENJEV_MODEL",
"format": "string",
"description": "Model alias used when a call does not name one (default: openjev)"
},
{
"name": "OPENJEV_TIMEOUT_MS",
"format": "number",
"description": "Per-attempt timeout in milliseconds, 1000-600000 (default: 30000)"
},
{
"name": "OPENJEV_MAX_RETRIES",
"format": "number",
"description": "Retries after the first attempt, 0-10 (default: 2)"
},
{
"name": "OPENJEV_BATCH_CONCURRENCY",
"format": "number",
"description": "Requests one jev_batch call keeps in flight at once, 1-16 (default: 4)"
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"openjev-mcp": {
"command": "npx",
"args": [
"-y",
"openjev-mcp@0.2.0"
],
"env": {
"OPENJEV_API_KEY": "<YOUR_OPENJEV_API_KEY>",
"OPENJEV_MODEL": "<YOUR_OPENJEV_MODEL>",
"OPENJEV_TIMEOUT_MS": "<YOUR_OPENJEV_TIMEOUT_MS>",
"OPENJEV_MAX_RETRIES": "<YOUR_OPENJEV_MAX_RETRIES>",
"OPENJEV_BATCH_CONCURRENCY": "<YOUR_OPENJEV_BATCH_CONCURRENCY>"
}
}
}
}Cline
{
"mcpServers": {
"openjev-mcp": {
"command": "npx",
"args": [
"-y",
"openjev-mcp@0.2.0"
],
"env": {
"OPENJEV_API_KEY": "<YOUR_OPENJEV_API_KEY>",
"OPENJEV_MODEL": "<YOUR_OPENJEV_MODEL>",
"OPENJEV_TIMEOUT_MS": "<YOUR_OPENJEV_TIMEOUT_MS>",
"OPENJEV_MAX_RETRIES": "<YOUR_OPENJEV_MAX_RETRIES>",
"OPENJEV_BATCH_CONCURRENCY": "<YOUR_OPENJEV_BATCH_CONCURRENCY>"
}
}
}
}VS Code
{
"servers": {
"openjev-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"openjev-mcp@0.2.0"
],
"env": {
"OPENJEV_API_KEY": "<YOUR_OPENJEV_API_KEY>",
"OPENJEV_MODEL": "<YOUR_OPENJEV_MODEL>",
"OPENJEV_TIMEOUT_MS": "<YOUR_OPENJEV_TIMEOUT_MS>",
"OPENJEV_MAX_RETRIES": "<YOUR_OPENJEV_MAX_RETRIES>",
"OPENJEV_BATCH_CONCURRENCY": "<YOUR_OPENJEV_BATCH_CONCURRENCY>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"openjev-mcp": {
"command": "npx",
"args": [
"-y",
"openjev-mcp@0.2.0"
],
"env": {
"OPENJEV_API_KEY": "<YOUR_OPENJEV_API_KEY>",
"OPENJEV_MODEL": "<YOUR_OPENJEV_MODEL>",
"OPENJEV_TIMEOUT_MS": "<YOUR_OPENJEV_TIMEOUT_MS>",
"OPENJEV_MAX_RETRIES": "<YOUR_OPENJEV_MAX_RETRIES>",
"OPENJEV_BATCH_CONCURRENCY": "<YOUR_OPENJEV_BATCH_CONCURRENCY>"
}
}
}
}Let your agent find its tools
Find servers like OpenJEV MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.