Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add task-orchestrator -- docker run -i --rm ghcr.io/jpicklyk/task-orchestrator:3.16.0~/.codex/config.toml
[mcp_servers.task-orchestrator]
command = "docker"
args = ["run", "-i", "--rm", "ghcr.io/jpicklyk/task-orchestrator:3.16.0"]
# codex mcp add task-orchestrator -- docker run -i --rm ghcr.io/jpicklyk/task-orchestrator:3.16.0~/.cursor/mcp.json
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
]
}
}
}.vscode/mcp.json
{
"servers": {
"task-orchestrator": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"task-orchestrator": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/jpicklyk/task-orchestrator:3.16.0"
]
}
}
}