random-agent
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@random-agent Orchestrate: research best practices for API design"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Random Agent
A powerful MCP server for multi-worker autonomous agent orchestration. Decompose complex tasks, run parallel workers, auto-review, and generate follow-up tasks — all through the Model Context Protocol.
Features
Parallel Workers — Run up to 5 concurrent AI agent processes
Task Decomposition — Auto-split complex tasks into subtasks with dependencies
Auto-Review & Reflection — Coordinator generates reviews and reflections on completed tasks
Follow-up Generation — Reflections auto-create new tasks for continuous improvement
22 Assertion Types — Validate outputs with equals, contains, regex, file-exists, json-path, and more
Stall Detection — Detect stuck workers, kill them, and auto-retry
Real-time Monitoring — Live status dashboard with queue counts and worker states
Metrics Collection — Track scores, issues, and patterns over time
Related MCP server: agent-mcp
Installation
git clone https://github.com/randomchips/random_agent.git
cd random_agent
npm install
npm run buildUsage
Add to your OpenCode config (~/.config/opencode/opencode.jsonc):
{
"mcp": {
"random-agent": {
"type": "local",
"command": ["node", "/path/to/random_agent/dist/index.js"],
"enabled": true,
"environment": {
"AGENT_OS_BASE_PATH": "C:\\agent-os"
}
}
}
}Tools
Tool | Description |
| Queue a task with name, command, priority, and optional assertions |
| Auto-decompose complex task → inject subtasks → monitor → return results |
| Live view: coordinator state, queue counts, active workers |
| Start / stop / restart the background coordinator loop |
| Detect stuck workers, kill them, auto-retry failed tasks |
| Run assertions on task output (22 assertion types) |
| Read coordinator logs, filter by search term or worker ID |
| Read metrics database (scores, issues, patterns) |
Pipeline Stages
inject → pending → in-progress → completed → review → reflection → follow-upInject — Task queued in
task-queue/pending/Worker — Spawns AI process, executes command
Completed — Task moved to
task-queue/completed/Review — AI generates review saved to
reviews/Reflection — AI generates reflection saved to
reflections/Follow-up — New tasks auto-generated for next cycle
Configuration
Environment variables:
Variable | Default | Description |
|
| Base path for all agent data |
|
| Max concurrent worker processes |
|
| Coordinator loop interval (seconds) |
|
| Seconds before worker is considered stuck |
Project Structure
random_agent/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── types.ts # TypeScript type definitions
│ ├── services/
│ │ ├── assertions.ts # Assertion engine (22 types)
│ │ ├── coordinator.ts # Coordinator lifecycle
│ │ ├── decomposer.ts # Task decomposition
│ │ ├── file-reader.ts # File system operations
│ │ └── worker-monitor.ts # Worker health monitoring
│ └── tools/
│ ├── assert.ts # Assert tool
│ ├── handle-stuck.ts # Handle stuck workers
│ ├── inject.ts # Inject tasks
│ ├── lifecycle.ts # Coordinator control
│ ├── logs.ts # Read logs
│ ├── metrics.ts # Read metrics
│ ├── orchestrate.ts # Full orchestration
│ └── status.ts # System status
├── package.json
├── tsconfig.json
└── README.mdLicense
MIT
Contributing
Contributions welcome! Open an issue or submit a PR at github.com/randomchips/random_agent.
Available Tools
8 toolsassertB
Run output comparison assertions on tasks or arbitrary text
Inputs: assertions (required), format, output, task_name.
coordinatorB
Start, stop, or restart the coordinator
Inputs: action (required).
handle_stuckA
Detect stuck/failed workers, kill them, and retry
Inputs: force.
injectC
Inject a task into the pending queue
Inputs: name (required), command (required), priority, assertions.
logsB
Read real log files from the agent-os system
Inputs: file, lines, search, worker_id.
metricsB
Read real metrics from the metrics database
Inputs: task, limit.
orchestrateB
Orchestrate a complex task: decompose, inject subtasks, monitor, return results
Inputs: description (required), wait, assertions, auto_start, +1 more.
statusA
Get live status: coordinator, queue counts, workers
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Tools are mostly distinct: metrics, status, and logs each read different data sources (DB, live coordinator state, files), while inject, orchestrate, handle_stuck, and coordinator manage different aspects of the system. However, metrics and status could be confused for overlapping system information.
Tool names mix nouns (metrics, status, logs, coordinator) with imperative verbs (inject, handle_stuck, orchestrate, assert). There is no consistent verb_noun or noun_verb pattern, making the set feel ad hoc.
Eight tools is well within the ideal 3-15 range for this domain. Each tool serves a distinct operational purpose without redundancy or bloat.
The set covers core operations: observability (metrics, status, logs), task injection, failure recovery, coordinator control, high-level orchestration, and assertion. Minor gaps exist (e.g., no direct task result retrieval outside orchestrate), but workflows are largely complete.
Maintenance
Related MCP Connectors
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
Design, build and run teams of AI agents with checked handoffs between them.
Task manager for AI agents. Orchestrate agents to achieve large goals in unified control plane.
- aXDeprecatedio.github.ax-platform
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceFacilitates autonomous AI agent collaboration on software projects through file-based task management and inter-agent communication via the Model Context Protocol.44 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables collaborative software development through a team of specialized AI agents (Architect, Developer, Reviewer, Tester) communicating via the Model Context Protocol, with tools for file management, task tracking, and code review.-
- AlicenseNot gradedqualityDmaintenanceProvides structured workflows (phases, gates, coordination) for AI agents, enabling complex task execution with quality enforcement and multi-agent coordination via Model Context Protocol.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA production-grade multi-agent workflow orchestrator built on the Model Context Protocol, featuring planner/executor/critic agents, durable run state, and replayable traces.15MIT