Switchback MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Switchback MCP recommend a model for fixing a typo in README"
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.
Switchback MCP
MCP server for Switchback — classify AI agent turns by complexity and pick the cheapest model that can handle them. Drop-in for Claude Desktop, Cursor, Cline, and any MCP client.
Built by VibeKit — same cascade router that powers every "Auto" turn in our hosted product. Learn more →
What it does
Exposes two tools over the Model Context Protocol:
classify_turn— given a user message, returns{tier: 0|1|2, why, fallback, durationMs}. Use it when you're deciding whether to spend on a flagship model or stay on a cheap one for the next agent step.recommend_model— given a user message + a ladder of models (cheap → flagship), returns the cheapest model on the ladder that can plausibly handle it. Convenience wrapper aroundclassify_turn.
Both tools fire a single small-model call via OpenRouter (default: openai/gpt-5.4-mini, ~$0.0001/call). Fail-soft: any error returns tier 1 with fallback: true rather than blocking your agent.
Related MCP server: oracle-models
Install
npm install -g vibekit-switchback-mcpConfigure
Set your OpenRouter key (get one at https://openrouter.ai/keys):
export OPENROUTER_API_KEY=sk-or-...Optional: override the classifier model:
export SWITCHBACK_CLASSIFIER_MODEL=anthropic/claude-haiku-4.5Claude Desktop
Add to your ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"switchback": {
"command": "npx",
"args": ["-y", "vibekit-switchback-mcp"],
"env": {
"OPENROUTER_API_KEY": "sk-or-..."
}
}
}
}Cursor / Cline / others
Any MCP client that supports stdio servers. Same npx invocation.
Example calls
classify_turn:
{
"userMessage": "rebuild the auth flow with passkeys"
}returns:
{
"tier": 2,
"why": "architectural rework + new auth method",
"fallback": false,
"durationMs": 412
}recommend_model:
{
"userMessage": "fix typo in README",
"ladder": [
"openai/gpt-5.4-mini",
"openai/gpt-5.4",
"openai/gpt-5.5"
]
}returns:
{
"recommended_model": "openai/gpt-5.4-mini",
"tier": 0,
"ladder_size": 3,
"classifier": { "tier": 0, "why": "trivial copy edit", "fallback": false, "durationMs": 318 }
}When to use it
Multi-step agents where you can swap models between rounds.
BYOK-style products where you want to keep all routing inside the user's chosen brand — pass a brand-locked ladder per user.
Cost-conscious orchestrators that want to avoid spending flagship rates on trivial turns.
When NOT to use it
One-shot chat completions where you can't change models after the first call — use OpenRouter's
autoor NotDiamond/Martian instead.Latency-critical sub-200ms-first-token UX — the classifier adds 200-500ms.
License
MIT. See LICENSE.
Built by VibeKit. The core library is vibekit-switchback — this package is the MCP wrapper.
Available Tools
2 toolsclassify_turnA
Classify how complex a user request is on a 0/1/2 scale. Use this when you're orchestrating an agent and want to decide whether to spend on a flagship model (tier 2), a mid-tier model (tier 1), or stay cheap (tier 0). Returns {tier, why, fallback, durationMs}.
Inputs: userMessage (required), recentHistory.
recommend_modelA
Given a ladder of models (cheap → flagship) and a user message, return the cheapest model on the ladder that can plausibly handle it, plus reasoning. The ladder should be brand-locked (all-Anthropic, all-OpenAI, etc.) to honor your user's BYOK provider.
Inputs: ladder (required), userMessage (required), recentHistory.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools both relate to routing user requests to models, so an agent could confuse classifying a turn with recommending a model. However, the inputs and outputs are distinct enough—one returns a tier, the other returns a specific model—to be workable with clear descriptions.
Both tools follow a consistent verb_noun snake_case pattern: classify_turn and recommend_model. Naming is predictable and clearly indicates the action and object.
With only two tools, the server feels thin, but the scope is narrow enough that both tools can earn their place. The count is borderline rather than egregiously insufficient.
The server covers the core routing workflow: classifying complexity and selecting a cost-appropriate model. Minor gaps exist, such as no combined route tool or ladder management, but agents can work around these using the provided inputs.
Maintenance
Related MCP Connectors
Cost-optimized LLM model routing recommendations for autonomous AI agents
Pay-per-call ($0.01 USDC) model-routing for AI coding agents: which LLM to call, cost vs. quality.
Reduces AI Agent token usage by 40% via three-stage SOP workflow.
Agent FinOps Spend Guard, Deterministic Budget Passport, LLM Token Cost Router & VIP Discounts.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA model routing advisor for autonomous agents — get cost-optimised LLM recommendations via MCP.5 npmMIT
- AlicenseAqualityDmaintenanceClassifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.328 npmMIT
- AlicenseAqualityDmaintenanceOptimizes token costs by intelligently delegating low-complexity tasks to local LLMs via LiteLLM, enabling cost-effective development workflows.31MIT
- AlicenseAqualityDmaintenancePre-execution cost estimation for LLM agent workflows, providing cost estimates before running tasks and improving accuracy over time through calibration.630 PyPI2MIT