x=hub

your toolset

    build deployment
    sign in

    Neo4j GDS Agent

    mcpkey · package official
    io.github.neo4j-contrib/gds-agent · v1.1.0
    deploy just this

    Neo4j Graph Data Science MCP server

    run it

    on your own machines, one way per deploy method
    generated from the record, not tested yet
    #!/usr/bin/env bash
# gds-agent (io.github.neo4j-contrib/gds-agent), recipe baremetal (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-gds-agent.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec uvx mcp-proxy --host 127.0.0.1 --port 8101 --pass-environment -- uvx gds-agent==1.1.0

[Unit]
Description=MCP server gds-agent (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/gds-agent
WorkingDirectory=/var/lib/mcp/gds-agent
ExecStart=/opt/mcp/my-agent/bin/gds-agent.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/gds-agent

[Install]
WantedBy=multi-user.target
    generated from the record, not tested yet
    docker run --rm -p 127.0.0.1:8101:8000 -e NEO4J_URI -e NEO4J_USERNAME -e NEO4J_PASSWORD -e NEO4J_DATABASE -e AURA_API_CLIENT_ID -e AURA_API_CLIENT_SECRET -e AURA_API_PROJECT_ID ghcr.io/astral-sh/uv:python3.12-bookworm-slim sh -c 'uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx gds-agent==1.1.0'
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T21:22:13+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:
  gds-agent:
    image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
    command:
    - sh
    - -c
    - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx gds-agent==1.1.0
    ports:
    - 127.0.0.1:8101:8000
    volumes:
    - uv-cache:/root/.cache/uv
    healthcheck:
      test:
      - CMD
      - python3
      - -c
      - import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/status')
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 2m
    restart: unless-stopped
    environment:
      NEO4J_URI: ${NEO4J_URI}
      NEO4J_USERNAME: ${NEO4J_USERNAME}
      NEO4J_PASSWORD: ${NEO4J_PASSWORD}
      NEO4J_DATABASE: ${NEO4J_DATABASE}
      AURA_API_CLIENT_ID: ${AURA_API_CLIENT_ID}
      AURA_API_CLIENT_SECRET: ${AURA_API_CLIENT_SECRET}
      AURA_API_PROJECT_ID: ${AURA_API_PROJECT_ID}
volumes:
  npm-cache: {}
  uv-cache: {}
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T21:22:13+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: gds-agent
  namespace: mcp
  labels: &id001
    app: gds-agent
spec:
  replicas: 1
  selector:
    matchLabels: *id001
  template:
    metadata:
      labels: *id001
    spec:
      containers:
      - name: gds-agent
        image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
        ports:
        - containerPort: 8000
          name: http
        env:
        - name: NEO4J_URI
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: NEO4J_URI
        - name: NEO4J_USERNAME
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: NEO4J_USERNAME
        - name: NEO4J_PASSWORD
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: NEO4J_PASSWORD
        - name: NEO4J_DATABASE
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: NEO4J_DATABASE
        - name: AURA_API_CLIENT_ID
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: AURA_API_CLIENT_ID
        - name: AURA_API_CLIENT_SECRET
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: AURA_API_CLIENT_SECRET
        - name: AURA_API_PROJECT_ID
          valueFrom:
            secretKeyRef:
              name: mcp-credentials
              key: AURA_API_PROJECT_ID
        command:
        - sh
        - -c
        - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx gds-agent==1.1.0
        readinessProbe:
          httpGet:
            path: /status
            port: http
          initialDelaySeconds: 10
---
apiVersion: v1
kind: Service
metadata:
  name: gds-agent
  namespace: mcp
spec:
  selector:
    app: gds-agent
  ports:
  - port: 8000
    targetPort: http
    name: http
    generated from the record, not tested yet
    # Generated by Hub for toolset "my-agent" (2026-10-17T21:22:13+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:
  gds-agent:
    enabled: true
    replicas: 1
    port: 8000
    path: /mcp
    container:
      name: gds-agent
      image: ghcr.io/astral-sh/uv:python3.12-bookworm-slim
      ports:
      - containerPort: 8000
        name: http
      env:
      - name: NEO4J_URI
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: NEO4J_URI
      - name: NEO4J_USERNAME
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: NEO4J_USERNAME
      - name: NEO4J_PASSWORD
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: NEO4J_PASSWORD
      - name: NEO4J_DATABASE
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: NEO4J_DATABASE
      - name: AURA_API_CLIENT_ID
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: AURA_API_CLIENT_ID
      - name: AURA_API_CLIENT_SECRET
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: AURA_API_CLIENT_SECRET
      - name: AURA_API_PROJECT_ID
        valueFrom:
          secretKeyRef:
            name: mcp-credentials
            key: AURA_API_PROJECT_ID
      command:
      - sh
      - -c
      - uvx mcp-proxy --host 0.0.0.0 --port 8000 --pass-environment -- uvx gds-agent==1.1.0
      readinessProbe:
        httpGet:
          path: /status
          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: NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, NEO4J_DATABASE, AURA_API_CLIENT_ID, AURA_API_CLIENT_SECRET, AURA_API_PROJECT_ID. 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
    uvx gds-agent==1.1.0
# env: NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, NEO4J_DATABASE, AURA_API_CLIENT_ID, AURA_API_CLIENT_SECRET, AURA_API_PROJECT_ID
    {
  "mcpServers": {
    "gds-agent": {
      "command": "uvx",
      "args": [
        "gds-agent==1.1.0"
      ],
      "env": {
        "NEO4J_URI": "${NEO4J_URI}",
        "NEO4J_USERNAME": "${NEO4J_USERNAME}",
        "NEO4J_PASSWORD": "${NEO4J_PASSWORD}",
        "NEO4J_DATABASE": "${NEO4J_DATABASE}",
        "AURA_API_CLIENT_ID": "${AURA_API_CLIENT_ID}",
        "AURA_API_CLIENT_SECRET": "${AURA_API_CLIENT_SECRET}",
        "AURA_API_PROJECT_ID": "${AURA_API_PROJECT_ID}"
      }
    }
  }
}
    #!/usr/bin/env bash
# Registers every server with Claude Code (run once; `claude mcp list` to check).
set -euo pipefail
set -a; [ -f .env ] && source .env; set +a
claude mcp add gds-agent -e "NEO4J_URI=${NEO4J_URI}" -e "NEO4J_USERNAME=${NEO4J_USERNAME}" -e "NEO4J_PASSWORD=${NEO4J_PASSWORD}" -e "NEO4J_DATABASE=${NEO4J_DATABASE}" -e "AURA_API_CLIENT_ID=${AURA_API_CLIENT_ID}" -e "AURA_API_CLIENT_SECRET=${AURA_API_CLIENT_SECRET}" -e "AURA_API_PROJECT_ID=${AURA_API_PROJECT_ID}" -- uvx gds-agent==1.1.0

    {
  "mcpServers": {
    "gds-agent": {
      "command": "uvx",
      "args": [
        "gds-agent==1.1.0"
      ],
      "env": {
        "NEO4J_URI": "${NEO4J_URI}",
        "NEO4J_USERNAME": "${NEO4J_USERNAME}",
        "NEO4J_PASSWORD": "${NEO4J_PASSWORD}",
        "NEO4J_DATABASE": "${NEO4J_DATABASE}",
        "AURA_API_CLIENT_ID": "${AURA_API_CLIENT_ID}",
        "AURA_API_CLIENT_SECRET": "${AURA_API_CLIENT_SECRET}",
        "AURA_API_PROJECT_ID": "${AURA_API_PROJECT_ID}"
      }
    }
  }
}
    {
  "servers": {
    "gds-agent": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "gds-agent==1.1.0"
      ],
      "env": {
        "NEO4J_URI": "${NEO4J_URI}",
        "NEO4J_USERNAME": "${NEO4J_USERNAME}",
        "NEO4J_PASSWORD": "${NEO4J_PASSWORD}",
        "NEO4J_DATABASE": "${NEO4J_DATABASE}",
        "AURA_API_CLIENT_ID": "${AURA_API_CLIENT_ID}",
        "AURA_API_CLIENT_SECRET": "${AURA_API_CLIENT_SECRET}",
        "AURA_API_PROJECT_ID": "${AURA_API_PROJECT_ID}"
      }
    }
  }
}
    name: my-agent
target: local
servers:
- hub: io.github.neo4j-contrib/gds-agent
    • not probed yet: tools unpinned, ingest lists them

    tools

    Probe result: faileddocker: the container exited: ^ | File "<path>", line 306, in send_request | raise McpError(response_or_error.error) | mcp.shared.exceptions.McpError: Connection closed +------------------------------------; baremetal: MCPError: Connection closed; server stderr: …ython3.12/site-packages/neo4j/_sync/driver.py", line 197, in driver driver_type, security_type, parsed = parse_neo4j_uri(uri) ^^^^^^^^^^^^^^^^^^^^ File "<path>", line 121, in parse_neo4j_uri raise ConfigurationError( neo4j.exceptions.C…

    runs · 1

    the latest tests of this entry by the hub and its workers, newest first
    dateworkermethodstatussandboxreason
    2026-10-17 11:36 local-mac-vm docker failed gvisor docker: the container exited: ^ | File "<path>", line 306, in send_request | raise McpError(response_or_error.error) | mcp.shared.exceptions.McpError: Connectio…