x=hub

your toolset

    build deployment
    sign in

    LLMVerify

    mcpkey · package
    io.github.subodhkc/llmverify · v1.8.0
    deploy just this

    Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    #!/usr/bin/env bash
# llmverify (io.github.subodhkc/llmverify), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-llmverify.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful --host 127.0.0.1 --port 8101 --streamableHttpPath /mcp --healthEndpoint /healthz

[Unit]
Description=MCP server llmverify (toolset my-agent), generated by Hub
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=mcp
Group=mcp
EnvironmentFile=/etc/mcp/my-agent.env
Environment=HOME=/var/lib/mcp/llmverify
WorkingDirectory=/var/lib/mcp/llmverify
ExecStart=/opt/mcp/my-agent/bin/llmverify.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/llmverify

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e LLMVERIFY_MCP_MAX_INPUT_CHARS -e LLMVERIFY_MCP_TIMEOUT_MS -e LLMVERIFY_MCP_MAX_OUTPUT_ITEMS -e LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS -e LLMVERIFY_HOME -e LLMVERIFY_AUDIT_DIR -e LLMVERIFY_LOG_DIR -e LLMVERIFY_BASELINE_DIR -e LLMVERIFY_USAGE_FILE -e LLMVERIFY_AUDIT_HASH_KEY -e LLMVERIFY_AUDIT_NO_CONTENT_HASH node:22-alpine sh -c 'npx -y supergateway@4 --stdio '"'"'npx -y [email protected]'"'"' --outputTransport streamableHttp --stateful --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T02:40:39+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:
  llmverify:
    image: node:22-alpine
    command:
    - sh
    - -c
    - npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful
      --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
    ports:
    - 127.0.0.1:8101:8000
    volumes:
    - npm-cache:/root/.npm
    healthcheck:
      test:
      - CMD-SHELL
      - wget -qO- http://127.0.0.1:8000/healthz || exit 1
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 2m
    restart: unless-stopped
    environment:
      LLMVERIFY_MCP_MAX_INPUT_CHARS: ${LLMVERIFY_MCP_MAX_INPUT_CHARS}
      LLMVERIFY_MCP_TIMEOUT_MS: ${LLMVERIFY_MCP_TIMEOUT_MS}
      LLMVERIFY_MCP_MAX_OUTPUT_ITEMS: ${LLMVERIFY_MCP_MAX_OUTPUT_ITEMS}
      LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS: ${LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS}
      LLMVERIFY_HOME: ${LLMVERIFY_HOME}
      LLMVERIFY_AUDIT_DIR: ${LLMVERIFY_AUDIT_DIR}
      LLMVERIFY_LOG_DIR: ${LLMVERIFY_LOG_DIR}
      LLMVERIFY_BASELINE_DIR: ${LLMVERIFY_BASELINE_DIR}
      LLMVERIFY_USAGE_FILE: ${LLMVERIFY_USAGE_FILE}
      LLMVERIFY_AUDIT_HASH_KEY: ${LLMVERIFY_AUDIT_HASH_KEY}
      LLMVERIFY_AUDIT_NO_CONTENT_HASH: ${LLMVERIFY_AUDIT_NO_CONTENT_HASH}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T02:40:39+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: llmverify
  namespace: mcp
  labels: &id001
    app: llmverify
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: llmverify
        image: node:22-alpine
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: LLMVERIFY_MCP_MAX_INPUT_CHARS
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_MCP_MAX_INPUT_CHARS
        - name: LLMVERIFY_MCP_TIMEOUT_MS
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_MCP_TIMEOUT_MS
        - name: LLMVERIFY_MCP_MAX_OUTPUT_ITEMS
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_MCP_MAX_OUTPUT_ITEMS
        - name: LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS
        - name: LLMVERIFY_HOME
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_HOME
        - name: LLMVERIFY_AUDIT_DIR
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_AUDIT_DIR
        - name: LLMVERIFY_LOG_DIR
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_LOG_DIR
        - name: LLMVERIFY_BASELINE_DIR
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_BASELINE_DIR
        - name: LLMVERIFY_USAGE_FILE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_USAGE_FILE
        - name: LLMVERIFY_AUDIT_HASH_KEY
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_AUDIT_HASH_KEY
        - name: LLMVERIFY_AUDIT_NO_CONTENT_HASH
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: LLMVERIFY_AUDIT_NO_CONTENT_HASH
        command:
        - sh
        - -c
        - npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful
          --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
        readinessProbe:
          httpGet:
            path: /healthz
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: llmverify
  namespace: mcp
spec:
  selector:
    app: llmverify
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-18T02:40:39+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:
  llmverify:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: llmverify
      image: node:22-alpine
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: LLMVERIFY_MCP_MAX_INPUT_CHARS
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_MCP_MAX_INPUT_CHARS
      - name: LLMVERIFY_MCP_TIMEOUT_MS
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_MCP_TIMEOUT_MS
      - name: LLMVERIFY_MCP_MAX_OUTPUT_ITEMS
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_MCP_MAX_OUTPUT_ITEMS
      - name: LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS
      - name: LLMVERIFY_HOME
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_HOME
      - name: LLMVERIFY_AUDIT_DIR
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_AUDIT_DIR
      - name: LLMVERIFY_LOG_DIR
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_LOG_DIR
      - name: LLMVERIFY_BASELINE_DIR
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_BASELINE_DIR
      - name: LLMVERIFY_USAGE_FILE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_USAGE_FILE
      - name: LLMVERIFY_AUDIT_HASH_KEY
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_AUDIT_HASH_KEY
      - name: LLMVERIFY_AUDIT_NO_CONTENT_HASH
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: LLMVERIFY_AUDIT_NO_CONTENT_HASH
      command:
      - sh
      - -c
      - npx -y supergateway@4 --stdio 'npx -y [email protected]' --outputTransport streamableHttp --stateful
        --host 0.0.0.0 --port 8000 --streamableHttpPath /mcp --healthEndpoint /healthz
      readinessProbe:
        httpGet:
          path: /healthz
          port: http
        initialDelaySeconds: 10

# 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
    deploy to koyeb

    The form opens with CHANGE_ME for each value you supply: LLMVERIFY_MCP_MAX_INPUT_CHARS, LLMVERIFY_MCP_TIMEOUT_MS, LLMVERIFY_MCP_MAX_OUTPUT_ITEMS, LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS, LLMVERIFY_HOME, LLMVERIFY_AUDIT_DIR, LLMVERIFY_LOG_DIR, LLMVERIFY_BASELINE_DIR, LLMVERIFY_USAGE_FILE, LLMVERIFY_AUDIT_HASH_KEY, LLMVERIFY_AUDIT_NO_CONTENT_HASH. Fill them in before you deploy.

    Clients connect to the service's https://…koyeb.app address plus /mcp.

    azure
    deploy to azuretemplate

    A Container Apps environment with one app per server, each with HTTPS ingress and one replica. The portal asks for each value you supply as a secure parameter; the deployment's outputs list the endpoints.

    connect to it

    copy what your client needs
    npx -y [email protected]
# env: LLMVERIFY_MCP_MAX_INPUT_CHARS, LLMVERIFY_MCP_TIMEOUT_MS, LLMVERIFY_MCP_MAX_OUTPUT_ITEMS, LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS, LLMVERIFY_HOME, LLMVERIFY_AUDIT_DIR, LLMVERIFY_LOG_DIR, LLMVERIFY_BASELINE_DIR, LLMVERIFY_USAGE_FILE, LLMVERIFY_AUDIT_HASH_KEY, LLMVERIFY_AUDIT_NO_CONTENT_HASH
    {
  "mcpServers": {
    "llmverify": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "LLMVERIFY_MCP_MAX_INPUT_CHARS": "${LLMVERIFY_MCP_MAX_INPUT_CHARS}",
        "LLMVERIFY_MCP_TIMEOUT_MS": "${LLMVERIFY_MCP_TIMEOUT_MS}",
        "LLMVERIFY_MCP_MAX_OUTPUT_ITEMS": "${LLMVERIFY_MCP_MAX_OUTPUT_ITEMS}",
        "LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS": "${LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS}",
        "LLMVERIFY_HOME": "${LLMVERIFY_HOME}",
        "LLMVERIFY_AUDIT_DIR": "${LLMVERIFY_AUDIT_DIR}",
        "LLMVERIFY_LOG_DIR": "${LLMVERIFY_LOG_DIR}",
        "LLMVERIFY_BASELINE_DIR": "${LLMVERIFY_BASELINE_DIR}",
        "LLMVERIFY_USAGE_FILE": "${LLMVERIFY_USAGE_FILE}",
        "LLMVERIFY_AUDIT_HASH_KEY": "${LLMVERIFY_AUDIT_HASH_KEY}",
        "LLMVERIFY_AUDIT_NO_CONTENT_HASH": "${LLMVERIFY_AUDIT_NO_CONTENT_HASH}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add llmverify -e "LLMVERIFY_MCP_MAX_INPUT_CHARS=${LLMVERIFY_MCP_MAX_INPUT_CHARS}" -e "LLMVERIFY_MCP_TIMEOUT_MS=${LLMVERIFY_MCP_TIMEOUT_MS}" -e "LLMVERIFY_MCP_MAX_OUTPUT_ITEMS=${LLMVERIFY_MCP_MAX_OUTPUT_ITEMS}" -e "LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS=${LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS}" -e "LLMVERIFY_HOME=${LLMVERIFY_HOME}" -e "LLMVERIFY_AUDIT_DIR=${LLMVERIFY_AUDIT_DIR}" -e "LLMVERIFY_LOG_DIR=${LLMVERIFY_LOG_DIR}" -e "LLMVERIFY_BASELINE_DIR=${LLMVERIFY_BASELINE_DIR}" -e "LLMVERIFY_USAGE_FILE=${LLMVERIFY_USAGE_FILE}" -e "LLMVERIFY_AUDIT_HASH_KEY=${LLMVERIFY_AUDIT_HASH_KEY}" -e "LLMVERIFY_AUDIT_NO_CONTENT_HASH=${LLMVERIFY_AUDIT_NO_CONTENT_HASH}" -- npx -y [email protected]

    {
  "mcpServers": {
    "llmverify": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "LLMVERIFY_MCP_MAX_INPUT_CHARS": "${LLMVERIFY_MCP_MAX_INPUT_CHARS}",
        "LLMVERIFY_MCP_TIMEOUT_MS": "${LLMVERIFY_MCP_TIMEOUT_MS}",
        "LLMVERIFY_MCP_MAX_OUTPUT_ITEMS": "${LLMVERIFY_MCP_MAX_OUTPUT_ITEMS}",
        "LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS": "${LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS}",
        "LLMVERIFY_HOME": "${LLMVERIFY_HOME}",
        "LLMVERIFY_AUDIT_DIR": "${LLMVERIFY_AUDIT_DIR}",
        "LLMVERIFY_LOG_DIR": "${LLMVERIFY_LOG_DIR}",
        "LLMVERIFY_BASELINE_DIR": "${LLMVERIFY_BASELINE_DIR}",
        "LLMVERIFY_USAGE_FILE": "${LLMVERIFY_USAGE_FILE}",
        "LLMVERIFY_AUDIT_HASH_KEY": "${LLMVERIFY_AUDIT_HASH_KEY}",
        "LLMVERIFY_AUDIT_NO_CONTENT_HASH": "${LLMVERIFY_AUDIT_NO_CONTENT_HASH}"
      }
    }
  }
}
    {
  "servers": {
    "llmverify": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "LLMVERIFY_MCP_MAX_INPUT_CHARS": "${LLMVERIFY_MCP_MAX_INPUT_CHARS}",
        "LLMVERIFY_MCP_TIMEOUT_MS": "${LLMVERIFY_MCP_TIMEOUT_MS}",
        "LLMVERIFY_MCP_MAX_OUTPUT_ITEMS": "${LLMVERIFY_MCP_MAX_OUTPUT_ITEMS}",
        "LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS": "${LLMVERIFY_MCP_MAX_TEXT_FIELD_CHARS}",
        "LLMVERIFY_HOME": "${LLMVERIFY_HOME}",
        "LLMVERIFY_AUDIT_DIR": "${LLMVERIFY_AUDIT_DIR}",
        "LLMVERIFY_LOG_DIR": "${LLMVERIFY_LOG_DIR}",
        "LLMVERIFY_BASELINE_DIR": "${LLMVERIFY_BASELINE_DIR}",
        "LLMVERIFY_USAGE_FILE": "${LLMVERIFY_USAGE_FILE}",
        "LLMVERIFY_AUDIT_HASH_KEY": "${LLMVERIFY_AUDIT_HASH_KEY}",
        "LLMVERIFY_AUDIT_NO_CONTENT_HASH": "${LLMVERIFY_AUDIT_NO_CONTENT_HASH}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.subodhkc/llmverify
    • not probed yet: tools unpinned, ingest lists them

    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.