jev-judge-mcp
projectotherio.github.pymodel/jev-judge-mcp · v
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, or escalate.
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
# once, as root:
docker build -t mcp-local/jev-judge:main 'https://github.com/pymodel/jev-judge-mcp.git#main'
#!/usr/bin/env bash
# jev-judge (io.github.pymodel/jev-judge-mcp), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-jev-judge.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-jev-judge -p 127.0.0.1:${PORT}:8000 mcp-local/jev-judge:main
[Unit]
Description=MCP server jev-judge (toolset my-agent), generated by Hub
After=network-online.target docker.service
Wants=network-online.target
[Service]
Type=simple
User=mcp
Group=mcp
SupplementaryGroups=docker
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/jev-judge
WorkingDirectory=/var/lib/mcp/jev-judge
ExecStart=/opt/mcp/my-agent/bin/jev-judge.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/jev-judge
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
docker build -t jev-judge 'https://github.com/pymodel/jev-judge-mcp.git#main' docker run --rm -p 127.0.0.1:8101:8000 jev-judge
generated from the record, not tested yet
CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
# Generated by Hub for toolset "my-agent" (2026-10-18T21:42:45+00:00).
# Each package server runs behind a stdio->HTTP bridge and listens on localhost only.
# cp .env.example .env # fill the ${VAR}s
# docker compose up -d && bash smoke.sh
# Remote servers are not here: clients reach them directly (see clients/).
name: mcp-my-agent
services:
jev-judge:
build:
context: https://github.com/pymodel/jev-judge-mcp.git#main
ports:
- 127.0.0.1:8101:8000
restart: unless-stopped
x-note: 'CHANGE_ME: built from the repository''s Dockerfile, assuming it serves streamable HTTP at
:8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.'
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
# Generated by Hub for toolset "my-agent" (2026-10-18T21:42:45+00:00).
# kubectl create namespace mcp
# kubectl -n mcp create secret generic mcp-credentials --from-env-file=.env
# kubectl apply -f kubernetes.yaml
# Services are cluster-internal: <name>.mcp.svc.cluster.local:8000/mcp. Put an ingress
# with auth in front before exposing any of them.
apiVersion: v1
kind: Namespace
metadata:
name: mcp
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: jev-judge
namespace: mcp
labels: &id001
app: jev-judge
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: jev-judge
image: CHANGE_ME
ports:
- containerPort: 8000
name: http
env: []
---
apiVersion: v1
kind: Service
metadata:
name: jev-judge
namespace: mcp
spec:
selector:
app: jev-judge
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
CHANGE_ME: built from the repository's Dockerfile, assuming it serves streamable HTTP at :8000/mcp. Nothing has run this yet; the worker replaces it with a tested recipe.
# Generated by Hub for toolset "my-agent" (2026-10-18T21:42:45+00:00).
# Credentials come from the Secret 'mcp-credentials' (kubectl create secret generic ... --from-env-file=.env).
# Each server under `servers` is one Deployment + Service; the keys after it configure
# upstream charts a worker verified.
servers:
jev-judge:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: jev-judge
image: CHANGE_ME
ports:
- containerPort: 8000
name: http
env: []
# helm install my-agent helm/my-agent -n mcp
in the cloud
one click: the provider's deploy form opens filled in, in your own account- koyeb
-
Clients connect to the service's https://…koyeb.app address plus /mcp.
- cloud run
-
Cloud Shell clones the repository, builds its Dockerfile and deploys it to Cloud Run.
Cloud Run sends requests to $PORT (8080); the recipe expects :8000, so the server has to read PORT, or set the container port on the service afterwards.
connect to it
copy what your client needs{
"mcpServers": {
"jev-judge": {
"command": "CHANGE_ME",
"args": []
}
}
}
#!/usr/bin/env bash # Registers every server with Claude Code (run once; `claude mcp list` to check). set -euo pipefail set -a; [ -f .env ] && source .env; set +a claude mcp add jev-judge -- CHANGE_ME
{
"mcpServers": {
"jev-judge": {
"command": "CHANGE_ME",
"args": []
}
}
}
{
"servers": {
"jev-judge": {
"type": "stdio",
"command": "CHANGE_ME",
"args": []
}
}
}
name: my-agent target: local servers: - hub: io.github.pymodel/jev-judge-mcp
- not probed yet: tools unpinned, ingest lists them
- no tested recipe for target 'local' yet: build it from https://github.com/PyModel/jev-judge-mcp by hand, or wait for the worker
tools
Not probed yetThe tools appear once the hub or its worker has listed this entry. Running it still works: your client lists them on first start.