Which integrations are available for this server?

Routes coding tasks to Amazon Q (Kiro) CLI as a secondary adapter, expanding provider options for task execution. Routes coding tasks to GitHub Copilot CLI for execution, leveraging its free gpt-5-mini tier for low-complexity work. Routes coding tasks to JetBrains Junie CLI, with medium-tier auto-routing by default for balanced performance. Routes coding tasks to OpenAI Codex CLI, enabling host shell and execution capabilities for AI-assisted development.

How do I use switchyard?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@switchyard refactor the login module and run tests on it" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

switchyard

by timjensgrossinger

Overview Schema Related Servers Score Discussions

Python

Local

Install in 2 minutes

curl -fsSL https://raw.githubusercontent.com/timjensgrossinger/switchyard/main/install.sh | bash

Or clone and install:

git clone https://github.com/timjensgrossinger/switchyard.git
cd switchyard
./install.sh

Requires: Python 3.10+, macOS or Linux, and at least one host AI CLI (gh, claude, gemini, codex, cursor-agent, junie, or opencode).

Restart your shell, then connect from Claude Code, Copilot CLI, Gemini, Codex, Cursor, or Junie — Switchyard registers as an MCP server automatically.

Related MCP server: Delegation MCP

Why Switchyard?


Save money	Route simple edits to free/low-tier models. Reserve opus/sonnet-class models for work that needs reasoning.
Use what you have	Works with GitHub Copilot, Claude Code, Gemini CLI, Codex, Cursor, Junie, OpenCode, Aider, Amazon Q/Kiro, and more — pick the cheapest authenticated CLI per task.
See everything	Every wave shows agent, tier, model, provider, and target files before and after execution.

Agents that learn — with your approval

Switchyard watches recurring work patterns, drafts reusable agents when evidence is strong, and waits for you to approve before anything goes live.

execute subtask → track patterns → draft agent → YOU approve → activate → auto-match future work

No auto-promotion — drafts never become active without explicit approval
Conservative gates — recurrence, quality score, and low rework must all agree before drafting
Project vs shared lanes — project-specific patterns activate sooner; shared patterns need stronger evidence
Inspect everything — learning_agent_summary, learning_pattern_health, and redacted learning_audit_log MCP tools

switchyard inspect approvals --project .
switchyard inspect approvals approve 12 --project . --operator you

How it works

You give a task to Copilot CLI, Claude Code, Gemini, or another MCP host.
Switchyard scores complexity → low / medium / high tier (no extra LLM call on the hot path).
Discovery picks the cheapest authenticated provider for that tier (excludes the caller to prevent recursion).
Complex tasks decompose into waves — independent subtasks run in parallel, dependents wait for prior waves.

Feature highlights

	Feature	What it does
🎯	Tier routing	Heuristic complexity scoring + intent modifiers (`quick` → cheaper, `production` → higher quality)
🔍	Live discovery	Scans installed CLIs, checks auth, ranks models by bundled cost data, caches in SQLite
🌊	Wave orchestration	`decompose_task` → parallel waves → integration verify; linear, DAG, hierarchical, and star topologies
🔌	MCP-native	~43 tools over stdio JSON-RPC; works with any MCP-compatible host shell
🧠	Warm-path eval	Background rework detection and quality scoring after subtasks complete
📈	Adaptive thresholds	EMA-based threshold learning from routing outcomes
🛡️	Write safety	Path validation, outside-workspace preview gate, audit trail
👁️	Operator CLI	`switchyard inspect`, `switchyard tune`, `switchyard doctor`, `switchyard-watch`

Supported providers

Provider	Binary	Routeable	Notes
GitHub Copilot	`gh`	✅	Core host; includes free `gpt-5-mini` low tier
Claude Code	`claude`	✅	haiku / sonnet / opus
Gemini CLI	`gemini`	✅	flash-lite / flash / pro
OpenCode	`opencode`	✅	Low-tier auto-route by default
OpenAI Codex	`codex`	✅	Host shell + execution
Cursor	`cursor-agent`	✅	Host shell + execution
JetBrains Junie	`junie`	✅	Medium-tier auto-route by default
Aider	`aider`	✅	Secondary adapter
Amazon Q / Kiro	`q` / `kiro`	✅	Secondary adapter
Mistral Vibe	`vibe`	✅	Secondary adapter
Blackbox AI	`blackbox`	✅	When CLI installed
Windsurf	`windsurf`	detect only	Never selected for execution

Run switchyard inspect status --project . --details for your live provider matrix.

Full compatibility matrix: docs/PROVIDER_COMPATIBILITY.md

See it in action

Before each wave:

📋 Wave 1 — Foundation files
┌─────────┬──────┬─────────────────────┬──────────────────┬─────────────────────────────┐
│ Agent # │ Tier │ Model               │ Provider         │ Target files                │
├─────────┼──────┼─────────────────────┼──────────────────┼─────────────────────────────┤
│ 1       │ low  │ gpt-5-mini          │ GitHub Copilot   │ config.py                   │
│ 2       │ low  │ gemini-2.5-flash-lite│ Gemini CLI      │ models.py                   │
│ 3       │ med  │ sonnet              │ Claude Code      │ main.py                     │
└─────────┴──────┴─────────────────────┴──────────────────┴─────────────────────────────┘

After all waves:

📊 Build complete — 3 agents, 1 wave
   GitHub Copilot: 1 agent (gpt-5-mini, free)
   Claude Code:    1 agent (sonnet, ~13k tokens)
   Gemini CLI:     1 agent (flash-lite, free)

Shell commands

ghc agent "implement JWT auth for the user service"   # multi-agent waves
ghcs "how to list files recursively in python"        # quick routed call
switchyard inspect status --project . --details       # provider readiness
switchyard-watch                                      # live TUI monitor

Full reference: docs/CLI.md

Documentation

Doc	Contents
MCP Tools	All 43 MCP tool surfaces
CLI Reference	Shell aliases and operator commands
Architecture	Trust boundaries and local-first design
Configuration	Safe starting config (copy to `~/.local/lib/switchyard/config.yaml`)
Model Discovery	Live catalogs, tier pins, cost ranks
Routing Quality	Eval methodology and accuracy
Release Limitations	Beta scope, privacy, roadmap
Troubleshooting	Common fixes

Beta status

Public beta v1.0.0-beta.1 — MCP tool schemas may change between releases; pin a git tag for stability. See CHANGELOG.md.

macOS and Linux; zsh and bash
Windows not supported by the installer
Provider behavior depends on locally installed CLI versions and entitlements

Running tests

SWITCHYARD_TEST_MODE=1 python3 -m pytest tests/ -q
SWITCHYARD_TEST_MODE=1 python3 -m shared.routing_eval
python3 scripts/check_release_archive.py

Uninstall

~/.local/lib/switchyard/uninstall.sh
~/.local/lib/switchyard/uninstall.sh --purge-data

License

Licensed under the Apache License, Version 2.0. Third-party attributions in NOTICE.

Built by @timjensgrossinger.

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

0dRelease cycle

3Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/timjensgrossinger/switchyard'

If you have feedback or need assistance with the MCP directory API, please join our Discord server