Muster MCP — AI skill for Claude Code
Rust core + MCP server for running many LLM agents in parallel without blowing your token budget — hard budget caps, automatic work dedup, and deterministic result merging.
How to install Muster MCP
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open JoasASantos/muster-mcp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Muster MCP does
Rust core + MCP server for running many LLM agents in parallel without blowing your token budget — hard budget caps, automatic work dedup, and deterministic result merging.
Alternatives in AI
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Open Researcher — 🔥 Visual AI research assistant that displays real-time thinking, provides split-view analysis, and automatic 634 ★
README
Muster
A reusable Rust core for **orchestrating many LLM agents in parallel** — exposed both as a linkable crate and as an MCP server.
*muster* — to assemble a force and bring it under command. That's the job: running one agent is easy; coordinating N of them without cost, redundant work, race conditions, and result-merge chaos getting out of hand is the hard part. With 3–6 concurrent agents, token use doesn't scale linearly — it explodes.
Muster exists to **impose budget, deduplicate work, and resolve result conflicts deterministically and auditably.** It does *not* implement the agents, the per-subtask logic, or the LLM client — the client is injected through a trait. Output verification is a separate layer.
🇧🇷 *Versão em português: [readme-pt.md](readme-pt.md).*
Install
Option A — prebuilt binary (recommended)
Grab the archive for your platform from the [latest release](https://github.com/JoasASantos/muster-mcp/releases/latest):
| Platform | Asset |
|---|---|
| Linux x86_64 | muster-mcp--x86_64-unknown-linux-gnu.tar.gz |
| Linux ARM64 | muster-mcp--aarch64-unknown-linux-gnu.tar.gz |
| macOS Intel | muster-mcp--x86_64-apple-darwin.tar.gz |
| macOS Apple Silicon | muster-mcp--aarch64-apple-darwin.tar.gz |
| Windows x86_64 | muster-mcp--x86_64-pc-windows-msvc.zip |
# macOS / Linux — extract and put it on your PATH
tar -xzf muster-mcp-*.tar.gz
install -m755 muster-mcp ~/.local/bin/muster-mcp # or anywhere on PATH
# register with Claude Code (user scope = available in every project)
claude mcp add --scope user muster -- ~/.local/bin/muster-mcp
claude mcp get muster # should say: ✔ Connected
Then **open a new Claude Code session** (MCP servers load at session start) and the `muster` tools appear. Released binaries include the optional Anthropic provider — set `ANTHROPIC_API_KEY` to use a real model; otherwise they run the built-i
Related Skills
Travel Planner Skill
AI travel-planning skill: one sentence in, a ready-to-go single-page guide out — true-scale maps, hard budget
Agent Loops
Deterministic agent loops for AI coding CLIs (Claude Code, Codex, Cursor, Kimi): worker + adversarial verifier
Laravel AI Translator
High quality automatic translate your language files into many languages using AI like Claude, GPT and etc.
Mem Budget
Show a 4-tier weighted context plan for a query (working/episodic/semantic/procedural) within a token budget.
Secondmate Reason
Ask a read-only reasoning model (via secondmate) a hard analysis question — root-cause, triage, plan review, p
Muster AI
Assemble your AI team — a multi-agent product management framework for Claude Code
Related Agents
Omd Persona Tester
Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget
Budget
AI cost engineering — LLM spend tracking, model cost optimization, budget alerts, token efficiency audits
Cost Forecaster
Forecasts GDD spend over the next N design cycles. Reads .design/telemetry/costs.jsonl (grouping est_cost_usd