Loading…
Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU
jevjam is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 78/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding jevjam to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
docker run -i --rm ghcr.io/beremaran/jevjam:0.3.3Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-04T14:32:37.177095Z",
"publishedAt": "2026-10-04T14:32:37.177095Z",
"statusChangedAt": "2026-10-04T14:32:37.177095Z"
}
},
"server": {
"name": "io.github.beremaran/jevjam",
"title": "jevjam",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.3.3",
"packages": [
{
"transport": {
"url": "http://localhost:8000/mcp",
"type": "streamable-http"
},
"identifier": "ghcr.io/beremaran/jevjam:0.3.3",
"runtimeHint": "docker",
"registryType": "oci",
"runtimeArguments": [
{
"name": "--gpus",
"type": "named",
"value": "all",
"description": "Give the container the host's NVIDIA GPUs (needs the NVIDIA Container Toolkit)"
},
{
"name": "-p",
"type": "named",
"value": "127.0.0.1:8000:8000",
"description": "Publish the HTTP API and MCP endpoint on loopback"
},
{
"name": "-v",
"type": "named",
"value": "jevjam-models:/models",
"description": "Keep downloaded checkpoints across restarts"
}
],
"environmentVariables": [
{
"name": "JEVJAM_API_KEY",
"isSecret": true,
"description": "When set, /mcp and /v1/systemone need 'Authorization: Bearer <key>'"
},
{
"name": "JEVJAM_IDLE_TIMEOUT",
"default": "300",
"description": "Seconds without inference before the resident checkpoint is freed; 0 keeps it"
},
{
"name": "HF_TOKEN",
"isSecret": true,
"description": "Optional Hugging Face token for higher download rate limits"
}
]
}
],
"repository": {
"url": "https://github.com/beremaran/jevjam",
"source": "github"
},
"websiteUrl": "https://github.com/beremaran/jevjam",
"description": "Typed decisions (choice, score, yes/no) from Laya, Julia-1 and clef-flash on your own GPU"
}
}