io.github.ynishi/mlua-swarm MCP Server

An MCP server for mlua-swarm that hosts a long-running swarm engine. It compiles flow.ir Blueprints and dispatches agent steps. A Blueprint defines a flow (step/seq/branch/loop/fanout/try/assign nodes) and the agents it references, then drives execution while recording task state.

🛠️ Key Features

Compiles flow.ir Blueprints
Dispatches agent steps to workers
Resolves agents to backends (in-process Lua, Rust function, child process, or interactive Operator)
Supports flow nodes: step, seq, branch, loop, fanout, try, assign

🚀 Use Cases

Run multi-agent workflows defined as Blueprints
Execute flows with mixed backends (Lua, Rust, child process, interactive Operator)
Maintain task state during flow execution

⚡ Developer Benefits

Blueprint-driven orchestration for agent step execution
Backend selection per referenced agent
Task state recording for flow runs

⚠️ Limitations

Information provided does not specify tool count, interfaces, or full MCP method coverage.

mlua-swarm

A long-running swarm engine host that compiles flow.ir Blueprints and dispatches their agent steps to workers. A Blueprint declares a flow (step / seq / branch / loop / fanout / try / assign nodes) plus the agents it references; the engine resolves each agent to a backend (in-process Lua, a Rust function, a child process, or an interactive Operator) and drives the flow while recording task state.

Install

bash

cargo install mlua-swarm-cli

This installs the mse binary with two subcommands:

bash

mse serve   # HTTP + WS server (tasks, Blueprint store, WS Operator sessions)
mse mcp     # MCP adapter over stdio, for AI agents (Claude Code etc.)

One-shot Blueprint execution is available through the swarm_run MCP tool (exposed by mse mcp), which runs through the canonical TaskApplication.handle / TaskLaunchService::launch path.

MCP client config:

json

{ "command": "mse", "args": ["mcp"] }

Docker (no Rust toolchain required)

Also listed on the MCP Registry as io.github.ynishi/mlua-swarm:

json

{
  "mcpServers": {
    "mlua-swarm": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "ghcr.io/ynishi/mse:latest",
        "mcp"
      ]
    }
  }
}

Documentation

Documentation is served from the code itself:

API / architecture — rustdoc on docs.rs (the crate root doc is the architecture overview).

Guides / samples / schema — bundled MCP resources under mse://, served by mse mcp and always version-matched to the binary: mse://guides/getting-started, mse://guides/bp-lifecycle (the develop → trial-run → operate workflow map), mse://guides/blueprint-authoring, mse://guides/mcp-tool-reference, mse://blueprints/samples/*, and the live Blueprint JSON Schema at mse://api/blueprint-schema (also available as the bp_schema tool).

crate

role

mlua-swarm

engine core (workspace root package)

mlua-swarm-schema

Blueprint schema types

mlua-swarm-server

HTTP + WS server library

mlua-swarm-cli

the mse binary

Install

Configuration

Arguments

subcommanddefault mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "mlua-swarm": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/ynishi/mse:0.29.0",
        "mcp"
      ]
    }
  }
}

io.github.ynishi/mlua-swarm