MCP Task Orchestrator
mcpotherio.github.jpicklyk/task-orchestrator · v3.16.0
Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates
run it
on your own machines, one way per deploy methodgenerated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
#!/usr/bin/env bash
# task-orchestrator (io.github.jpicklyk/task-orchestrator), recipe docker (generated).
# Generated by Hub for toolset "my-agent"; started by mcp-my-agent-task-orchestrator.service.
set -euo pipefail
export HOST=127.0.0.1 PORT=8101
exec docker run --rm --name mcp-my-agent-task-orchestrator -p 127.0.0.1:${PORT}:8000 --env-file /etc/mcp/my-agent.env ghcr.io/jpicklyk/task-orchestrator:3.16.0
[Unit]
Description=MCP server task-orchestrator (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/task-orchestrator
WorkingDirectory=/var/lib/mcp/task-orchestrator
ExecStart=/opt/mcp/my-agent/bin/task-orchestrator.sh
Restart=on-failure
RestartSec=5
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
PrivateTmp=true
ReadWritePaths=/var/lib/mcp/task-orchestrator
[Install]
WantedBy=multi-user.target
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
docker run --rm -p 127.0.0.1:8101:8000 -e DATABASE_PATH -e USE_FLYWAY -e AGENT_CONFIG_DIR -e MCP_TRANSPORT -e MCP_HTTP_PORT -e LOG_LEVEL -e LOG_FILE ghcr.io/jpicklyk/task-orchestrator:3.16.0
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:31:06+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:
task-orchestrator:
image: ghcr.io/jpicklyk/task-orchestrator:3.16.0
ports:
- 127.0.0.1:8101:8000
restart: unless-stopped
x-note: 'CHANGE_ME: check the image''s README for its transport and port; this assumes streamable
HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command
instead.'
environment:
DATABASE_PATH: ${DATABASE_PATH}
USE_FLYWAY: ${USE_FLYWAY}
AGENT_CONFIG_DIR: ${AGENT_CONFIG_DIR}
MCP_TRANSPORT: ${MCP_TRANSPORT}
MCP_HTTP_PORT: ${MCP_HTTP_PORT}
LOG_LEVEL: ${LOG_LEVEL}
LOG_FILE: ${LOG_FILE}
volumes:
npm-cache: {}
uv-cache: {}
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:31:06+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: task-orchestrator
namespace: mcp
labels: &id001
app: task-orchestrator
spec:
replicas: 1
selector:
matchLabels: *id001
template:
metadata:
labels: *id001
spec:
containers:
- name: task-orchestrator
image: ghcr.io/jpicklyk/task-orchestrator:3.16.0
ports:
- containerPort: 8000
name: http
env:
- name: DATABASE_PATH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: DATABASE_PATH
- name: USE_FLYWAY
valueFrom:
secretKeyRef:
name: mcp-credentials
key: USE_FLYWAY
- name: AGENT_CONFIG_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AGENT_CONFIG_DIR
- name: MCP_TRANSPORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_TRANSPORT
- name: MCP_HTTP_PORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_HTTP_PORT
- name: LOG_LEVEL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_LEVEL
- name: LOG_FILE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_FILE
---
apiVersion: v1
kind: Service
metadata:
name: task-orchestrator
namespace: mcp
spec:
selector:
app: task-orchestrator
ports:
- port: 8000
targetPort: http
name: http
generated from the record, not tested yet
CHANGE_ME: check the image's README for its transport and port; this assumes streamable HTTP at :8000/mcp. If it speaks stdio only, use it from clients/mcp.json as a `docker run -i` command instead.
# Generated by Hub for toolset "my-agent" (2026-10-18T05:31:06+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:
task-orchestrator:
enabled: true
replicas: 1
port: 8000
path: /mcp
container:
name: task-orchestrator
image: ghcr.io/jpicklyk/task-orchestrator:3.16.0
ports:
- containerPort: 8000
name: http
env:
- name: DATABASE_PATH
valueFrom:
secretKeyRef:
name: mcp-credentials
key: DATABASE_PATH
- name: USE_FLYWAY
valueFrom:
secretKeyRef:
name: mcp-credentials
key: USE_FLYWAY
- name: AGENT_CONFIG_DIR
valueFrom:
secretKeyRef:
name: mcp-credentials
key: AGENT_CONFIG_DIR
- name: MCP_TRANSPORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_TRANSPORT
- name: MCP_HTTP_PORT
valueFrom:
secretKeyRef:
name: mcp-credentials
key: MCP_HTTP_PORT
- name: LOG_LEVEL
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_LEVEL
- name: LOG_FILE
valueFrom:
secretKeyRef:
name: mcp-credentials
key: LOG_FILE
# 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
-
The form opens with CHANGE_ME for each value you supply: DATABASE_PATH, USE_FLYWAY, AGENT_CONFIG_DIR, MCP_TRANSPORT, MCP_HTTP_PORT, LOG_LEVEL, LOG_FILE. Fill them in before you deploy.
Clients connect to the service's https://…koyeb.app address plus /mcp.
- azure
-
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 needsdocker run -i --rm -e DATABASE_PATH -e USE_FLYWAY -e AGENT_CONFIG_DIR -e MCP_TRANSPORT -e MCP_HTTP_PORT -e LOG_LEVEL -e LOG_FILE ghcr.io/jpicklyk/task-orchestrator:3.16.0
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"DATABASE_PATH",
"-e",
"USE_FLYWAY",
"-e",
"AGENT_CONFIG_DIR",
"-e",
"MCP_TRANSPORT",
"-e",
"MCP_HTTP_PORT",
"-e",
"LOG_LEVEL",
"-e",
"LOG_FILE",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
],
"env": {
"DATABASE_PATH": "${DATABASE_PATH}",
"USE_FLYWAY": "${USE_FLYWAY}",
"AGENT_CONFIG_DIR": "${AGENT_CONFIG_DIR}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"MCP_HTTP_PORT": "${MCP_HTTP_PORT}",
"LOG_LEVEL": "${LOG_LEVEL}",
"LOG_FILE": "${LOG_FILE}"
}
}
}
}
#!/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 task-orchestrator -e "DATABASE_PATH=${DATABASE_PATH}" -e "USE_FLYWAY=${USE_FLYWAY}" -e "AGENT_CONFIG_DIR=${AGENT_CONFIG_DIR}" -e "MCP_TRANSPORT=${MCP_TRANSPORT}" -e "MCP_HTTP_PORT=${MCP_HTTP_PORT}" -e "LOG_LEVEL=${LOG_LEVEL}" -e "LOG_FILE=${LOG_FILE}" -- docker run -i --rm -e DATABASE_PATH -e USE_FLYWAY -e AGENT_CONFIG_DIR -e MCP_TRANSPORT -e MCP_HTTP_PORT -e LOG_LEVEL -e LOG_FILE ghcr.io/jpicklyk/task-orchestrator:3.16.0
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"DATABASE_PATH",
"-e",
"USE_FLYWAY",
"-e",
"AGENT_CONFIG_DIR",
"-e",
"MCP_TRANSPORT",
"-e",
"MCP_HTTP_PORT",
"-e",
"LOG_LEVEL",
"-e",
"LOG_FILE",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
],
"env": {
"DATABASE_PATH": "${DATABASE_PATH}",
"USE_FLYWAY": "${USE_FLYWAY}",
"AGENT_CONFIG_DIR": "${AGENT_CONFIG_DIR}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"MCP_HTTP_PORT": "${MCP_HTTP_PORT}",
"LOG_LEVEL": "${LOG_LEVEL}",
"LOG_FILE": "${LOG_FILE}"
}
}
}
}
{
"servers": {
"task-orchestrator": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"DATABASE_PATH",
"-e",
"USE_FLYWAY",
"-e",
"AGENT_CONFIG_DIR",
"-e",
"MCP_TRANSPORT",
"-e",
"MCP_HTTP_PORT",
"-e",
"LOG_LEVEL",
"-e",
"LOG_FILE",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
],
"env": {
"DATABASE_PATH": "${DATABASE_PATH}",
"USE_FLYWAY": "${USE_FLYWAY}",
"AGENT_CONFIG_DIR": "${AGENT_CONFIG_DIR}",
"MCP_TRANSPORT": "${MCP_TRANSPORT}",
"MCP_HTTP_PORT": "${MCP_HTTP_PORT}",
"LOG_LEVEL": "${LOG_LEVEL}",
"LOG_FILE": "${LOG_FILE}"
}
}
}
}
name: my-agent target: local servers: - hub: io.github.jpicklyk/task-orchestrator
- 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.