1. Conduid
  2. Developer Tools
  3. orc8
MCP server · Developer Tools

orc8

A dynamic orchestration library for A2A enabled AI agents that can call MCP servers.

Unclaimed devtools
39Low

Scored 5 months ago · breakdown

About orc8

orc8 is an MCP server published by git+the-artinet-project in the Developer Tools category: a dynamic orchestration library for A2A enabled AI agents that can call MCP servers.

Install

Install
npx orc8
Claude Code
claude mcp add artinet -- npx -y orc8
npx
npx -y orc8

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about orc8

Powered by Claude · Grounded in docs

I know everything about orc8. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

4 checks have not been run yet.

README

Build, deploy, and orchestrate AI agents that communicate across frameworks using standard protocols from the Agentic AI Foundation.

Packages

Package Description npm
@artinet/sdk Core SDK for building A2A agents with client/server support npm
cruiser Convert Openai/Anthropic/Langchain/etc agents into A2A agents npm
fleet Server framework for hosting A2A agents with MCP integration npm
agent-relay Agent discovery and multi-agent communication npm
orc8 Dynamic orchestration for A2A agents with MCP tool support npm
symphony Interactive CLI for managing multi-agent systems npm
create-agent CLI tool to scaffold A2A agent projects npm
ask Lightweight CLI chat client for A2A servers npm
load Load agent definitions from files npm
agent-def Standardized agent definition schema npm
types Shared TypeScript types npm
mcp MCP servers (bash, agent-relay) npm npm

Quick Start

Create an Agent

npx @artinet/create-agent@latest

Own every line

Server:

Serve intelligence in a couple lines. cr8 lets you quickly scaffold an AI agent without the headache.

import { cr8 } from "@artinet/sdk";

const { app } = cr8("My Agent")
  .text(({ content }) => `You said: ${content}`)
  .server.start(3000);

Messenger:

Talk to any agent. Messenger is an A2A protocol client, purpose built for multi-agent servers.

import { createMessenger, AgentMessenger } from "@artinet/sdk";

const messenger: AgentMessenger = createMessenger({
  baseUrl: "http://localhost:3000/a2a",
});

for await (const update of messenger.sendMessageStream("Hello!")) {
  console.log(update);
}

One protocol, Every framework

Cruiser docks agents from any framework onto artinet. Letting your OpenAI, Claude, and LangChain agents collaborate.

import { Agent } from "@openai/agents";
import { dock } from "@artinet/cruiser/openai";
import { serve } from "@artinet/sdk";

const openaiAgent = new Agent({
  name: "assistant",
  instructions: "You are a helpful assistant",
});

const agent = await dock(agent, { name: "My Assistant" });

await agent.sendMessage("Hello, World!");

Ship agents, not infrastructure.

Fleet is a lightweight server that deploys A2A AI agents, so you can focus on intelligence, not plumbing.

import { fleet } from "@artinet/fleet/express";
import { createMessenger, AgentMessenger } from "@artinet/sdk";

const flotilla = await fleet().ship([
  {
    config: {
      uri: "my-agent",
      ...
    },
  },
]);

flotilla.launch(3000);

const messenger: AgentMessenger = await createMessenger({ baseUrl: "http://localhost:3000/agentId/my-agent" });

await messenger.sendMessage("Hello, World!");

Architecture

┌─────────────────────────────────────────────────────────────────┐
│                        Artinet Platform                         │
├─────────────────────────────────────────────────────────────────┤
│  CLI Tools                                                      │
│  ├── create-agent         → Scaffold new projects               │
│  ├── symphony             → Multi-agent management              │
│  └── ask                  → Chat with agents                    │
├─────────────────────────────────────────────────────────────────┤
│  Server Frameworks                                              │
│  ├── fleet                → Deploy & host agents                │
│  └── sdk                  → Build A2A servers                   │
├─────────────────────────────────────────────────────────────────┤
│  Agent Building                                                 │
│  ├── orc8                 → Orchestration + MCP tools           │
│  ├── cruiser              → Framework adapter (Langchain, etc)  │
│  └── relay                → Agent discovery                     │
├─────────────────────────────────────────────────────────────────┤
│  Foundation                                                     │
│  ├── agent-def            → Agent definition schema             │
│  ├── loader               → Load definitions from files         │
│  ├── types                → Shared types                        │
│  └── mcp/                 → MCP servers (bash, relay)           │
└─────────────────────────────────────────────────────────────────┘

Requirements

  • Node.js ≥ 18.9.1 (Recommended: 20 or ≥ 22)

License

Apache-2.0

Contributing

Contributions welcome! Please open an issue or PR on GitHub.

Links

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About orc8

How do I install orc8?

Run npx orc8, then add the server to your MCP client's configuration.

Is orc8 safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 2 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is orc8 still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.