mlua-swarm MCP server
Commit Oct 19, 2026Compiles flow.ir Blueprints and dispatches agent steps to various backends like Lua, Rust, or child processes.
Also known as ynishi/mlua-swarm
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.32.1
- Last commit
- Oct 19, 2026
- License
- Apache-2.0
What is mlua-swarm MCP?
mlua-swarm compiles flow.ir Blueprints and dispatches agent steps to various backends like Lua, Rust, or child processes.
Summary generated from the project's README
About mlua-swarm MCP server
Compiling flow.ir Blueprints and managing agent execution across different backends is what mlua-swarm enables for developers building complex agentic workflows. The engine processes various node types including step, seq, branch, loop, fanout, try, and let nodes to drive automated flows. It resolves agents to specific environments such as in-process Lua, Rust functions, child processes, or interactive Operators while maintaining a record of task state.
Users can connect via an MCP adapter using the mse binary through stdio or by running a Docker container. The system provides a swarm_run tool for one-shot Blueprint execution and offers several resources through the mse:// protocol. These resources include getting started guides, blueprint lifecycle documentation, and a live Blueprint JSON Schema accessible via the bp_schema tool. This setup allows AI clients like Claude Code to interact directly with the swarm engine to manage and execute structured agent tasks.
What you can do with it
- 1Execute single agent workflowsAn AI agent can trigger a specific Blueprint execution using the swarm_run tool.
- 2Access technical documentationDevelopers can retrieve implementation guides and schema definitions directly through MCP resources.
- 3Validate blueprint structuresYou can use the bp_schema tool to check your Blueprint JSON against the live schema.
- 4Deploy without Rust toolchainYou can run the server using Docker to avoid local compilation requirements.
Written from the project's README. Every use case is checked against a quote from it.
How to install mlua-swarm MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall mlua-swarm MCP in Claude Code
$ claude mcp add mlua-swarm -- docker run -i --rm ghcr.io/ynishi/mse:0.32.1Install mlua-swarm MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mlua-swarm": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.32.1"
]
}
}
}Install mlua-swarm MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mlua-swarm": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.32.1"
]
}
}
}Install mlua-swarm MCP in VS Code CLI
$ code --add-mcp '{"name":"mlua-swarm","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/ynishi/mse:0.32.1"]}'Install mlua-swarm MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mlua-swarm": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.32.1"
]
}
}
}Install mlua-swarm MCP in Codex
$ codex mcp add mlua-swarm -- docker run -i --rm ghcr.io/ynishi/mse:0.32.1Install mlua-swarm MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mlua-swarm] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/ynishi/mse:0.32.1"]
Install mlua-swarm MCP in Gemini CLI
$ gemini mcp add -s user mlua-swarm docker -- run -i --rm ghcr.io/ynishi/mse:0.32.1Install mlua-swarm MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mlua-swarm": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/ynishi/mse:0.32.1"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableynishi/mlua-swarm is public and reachablegithub.com/ynishi/mlua-swarm ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-19github.com/ynishi/mlua-swarm ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubmlua-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
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.
mlua-swarm MCP questions
How do I add mlua-swarm MCP to Claude Code?
Run claude mcp add mlua-swarm -- docker run -i --rm ghcr.io/ynishi/mse:0.32.1 in your terminal. Add --scope user to make it available in every project.
How do I add mlua-swarm MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I install the mlua-swarm CLI?
You can install it using cargo with the command: cargo install mlua-swarm-cli.
Can I run mlua-swarm using Docker?
Yes, you can run it via Docker without needing a Rust toolchain by using the ghcr.io/ynishi/mse:latest image.
What kind of backends does the engine support for agents?
The engine resolves agents to in-process Lua, Rust functions, child processes, or interactive Operators.
Where can I find documentation and Blueprint schemas?
Documentation and schemas are bundled as MCP resources under the mse:// prefix, such as mse://guides/getting-started and mse://api/blueprint-schema.