Mlua Swarm

io.github.ynishiPublished by GitHub account ynishiv0.32.1Updated Oct 24, 2026

MCP server for mlua-swarm: engine that compiles flow.ir Blueprints and dispatches agent steps.

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

MCP adapter for the mlua-swarm engine that compiles flow.ir Blueprints and dispatches their agent steps to workers.

What you can do
  • Run a Blueprint in one shot through the swarm_run tool, going through the engine's canonical task launch path.
  • Read bundled documentation resources under mse://, including getting-started, Blueprint lifecycle, authoring and MCP tool reference guides.
  • Fetch sample Blueprints and the live Blueprint JSON Schema, also exposed as the bp_schema tool.
  • Drive flows made of step, seq, branch, loop, fanout, try and let nodes, with agents resolved to in-process Lua, Rust functions, child processes or an interactive Operator.
When to use it
Useful when you want an assistant to author, validate and execute mlua-swarm Blueprints and orchestrate multi-step agent workflows from a single MCP session. It fits teams already using the mlua-swarm engine rather than general-purpose automation.
Requirements
Runs locally over stdio. Either install the mse binary via cargo install mlua-swarm-cli and configure the command mse with args mcp, or run the published container image with docker run -i --rm and the mcp argument. No authentication, environment variables or headers are declared.
Before you install
Executing a Blueprint dispatches agent steps that may run child processes or hand control to an interactive Operator, so review what a Blueprint references before running it. The engine also records task state; the separate mse serve mode exposes an HTTP and WebSocket server.

Installation

In SourceWeft

  1. Open Mlua Swarm in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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 / let 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).

Workspace crates

craterole
mlua-swarmengine core (workspace root package)
mlua-swarm-schemaBlueprint schema types
mlua-swarm-serverHTTP + WS server library
mlua-swarm-clithe mse binary

License

Licensed under either of Apache License 2.0 or MIT License at your option.

Source: README.md at commit 97e2112

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

5
  1. v0.32.1LatestOct 19, 2026
  2. v0.32.0Oct 19, 2026
  3. v0.31.0Oct 18, 2026
  4. v0.30.0Oct 18, 2026
  5. v0.29.0Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts