oci ghcr.io/ynishi/mse:0.27.0stdioApache-2.0updated 13d ago
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.
mlua swarm 能做什么?
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
cargo install mlua-swarm-cli
This installs the mse binary with two subcommands:
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:
{ "command": "mse", "args": ["mcp"] }
Docker (no Rust toolchain required)
Also listed on the MCP Registry
as io.github.ynishi/mlua-swarm:
{
"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 bymse mcpand 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 atmse://api/blueprint-schema(also available as thebp_schematool).
Workspace crates
| 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 |
License
Licensed under either of Apache License 2.0 or MIT License at your option.
安装
把 mlua swarm 添加到你的客户端。选择你正在使用的那个。
claude mcp add ghcr-io-ynishi-mse-0-27-0 -- docker run -i --rm ghcr.io/ynishi/mse:0.27.0codex mcp add ghcr-io-ynishi-mse-0-27-0 -- docker run -i --rm ghcr.io/ynishi/mse:0.27.0amp mcp add ghcr-io-ynishi-mse-0-27-0 -- docker run -i --rm ghcr.io/ynishi/mse:0.27.0{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}Add to `claude_desktop_config.json`, then restart Claude Desktop.
{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}Add to `~/.cursor/mcp.json`, or `.cursor/mcp.json` for a single project.
code --add-mcp '{"name":"ghcr-io-ynishi-mse-0-27-0","command":"docker","args":["run","-i","--rm","ghcr.io/ynishi/mse:0.27.0"]}'Or add the block manually to `.vscode/mcp.json` under `servers`.
{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}Add to `~/.codeium/windsurf/mcp_config.json`.
{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}Add to `cline_mcp_settings.json` via the MCP Servers panel.
{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}Add to `~/.gemini/settings.json`.
{
"mcpServers": {
"ghcr-io-ynishi-mse-0-27-0": {
"type": "local",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
],
"tools": [
"*"
]
}
}
}Add to `~/.copilot/mcp-config.json`, or run `/mcp add` inside the CLI.
{
"context_servers": {
"ghcr-io-ynishi-mse-0-27-0": {
"command": {
"path": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.27.0"
]
}
}
}
}Add to your Zed `settings.json`.
docker run -i --rm ghcr.io/ynishi/mse:0.27.0Run `goose configure`, choose **Add Extension → Command-line Extension**, and paste this command.
评分
39 / 100
不完整
- 文档22/25
- 维护25/25
- 可信度13/20
- 能力0/15
- 安装体验12/15
- Documents what it does and how to connect
- Has a resolvable package or endpoint
- Exposes at least one tool, prompt or resource
- README has substantive content
- Includes a code example
- Documents its configuration
- Mentions credentials or security posture
- Last commit 5 days ago
- Has a release history
- Repository is not archived
- Licensed Apache-2.0
- Namespace verified in the official MCP registry
- Claimed by its owner
- Published under an organisation
- 0 tool(s) documented
- Provides prompt templates
- Provides resources
- 12 documented install method(s)
- Published to a package registry
- Offers a hosted endpoint — no local install
版本历史
| 版本 | 发布于 |
|---|---|
| 0.27.0最新 | 2026年8月27日 |
| 0.26.0 | 2026年8月14日 |
| 0.25.0 | 2026年8月10日 |
| 0.24.0 | 2026年8月6日 |
| 0.23.1 | 2026年8月5日 |
| 0.23.0 | 2026年8月1日 |
| 0.22.0 | 2026年8月1日 |
| 0.21.0 | 2026年7月31日 |
| 0.20.0 | 2026年7月30日 |
| 0.19.0 | 2026年7月30日 |
| 0.18.0 | 2026年7月25日 |
| 0.17.0 | 2026年7月24日 |
| 0.16.0 | 2026年7月24日 |
| 0.15.0 | 2026年7月23日 |
| 0.14.1 | 2026年7月20日 |
| 0.14.0 | 2026年7月19日 |
| 0.13.0 | 2026年7月19日 |
| 0.12.3 | 2026年7月18日 |
| 0.12.2 | 2026年7月18日 |
| 0.12.1 | 2026年7月17日 |
| 0.12.0 | 2026年7月17日 |
| 0.11.0 | 2026年7月16日 |
| 0.10.0 | 2026年7月14日 |
| 0.9.2 | 2026年7月12日 |
| 0.9.1 | 2026年7月11日 |
| 0.9.0 | 2026年7月10日 |
| 0.8.0 | 2026年7月9日 |
| 0.7.0 | 2026年7月9日 |
| 0.6.0 | 2026年7月8日 |
| 0.5.0 | 2026年7月7日 |
| 0.4.1 | 2026年7月6日 |
| 0.4.0 | 2026年7月6日 |
| 0.3.0 | 2026年7月5日 |
| 0.2.1 | 2026年7月5日 |
| 0.2.0 | 2026年7月5日 |
| 0.1.4 | 2026年7月5日 |
| 0.1.3 | 2026年7月4日 |