Skip to main content
Glama
deenesjakoruzh
VibeKit-Bot

Switchback MCP

by VibeKit-Bot
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

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.

npm Powers VibeKit

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 around classify_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-mcp

Configure

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-4.5

Claude 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 auto or 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 tools
classify_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}.

ParametersJSON Schema
NameRequiredDescriptionDefault
userMessageYesThe user's request to classify. Capped at 1500 chars internally.
recentHistoryNoOptional. Last 1-2 assistant turns for context. Each capped at 200 chars internally.

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does disclose the return shape ({tier, why, fallback, durationMs}) and explains the tier meanings, which adds value. However, it does not disclose potential side effects, fallback semantics, or internal behavior such as truncation limits beyond what the schema already contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core action and scale, then followed by the use case and return shape. Every sentence earns its place with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema is simple and the description covers purpose, use case, and return fields, but it does not explain the meanings of 'fallback' and 'durationMs', nor does it contrast with the sibling 'recommend_model'. This leaves gaps an agent might need to resolve before confidently choosing this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add parameter-specific detail beyond the schema; it only explains the tier scale, not how userMessage or recentHistory should be formatted beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description states a specific verb ('Classify'), a resource ('user request'), and the 0/1/2 scale, making the tool's purpose immediately clear. It also ties the scale to model-tier decisions, but it does not explicitly differentiate from the sibling tool 'recommend_model'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says when to use it ('when you're orchestrating an agent and want to decide whether to spend...'), giving clear context for deployment. However, it does not state when not to use it or mention the alternative tool, so it lacks exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema
NameRequiredDescriptionDefault
ladderYesOrdered model ids, index 0 = cheapest. Example: ['openai/gpt-5.4-mini', 'openai/gpt-5.4', 'openai/gpt-5.5']
userMessageYesThe user's request.
recentHistoryNoOptional context. Last 1-2 assistant turns.

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden of explaining behavior. It states the tool returns a recommendation plus reasoning and enforces a brand-locked ladder, but it does not disclose what happens when no model is suitable, how 'plausibly' is determined, or whether the tool actually invokes any external model.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The primary behavior is front-loaded in the first sentence, and the BYOK constraint earns its place in the second sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description appropriately explains the expected return: cheapest model plus reasoning. It could be more explicit about edge cases, such as an incapable ladder or how 'recentHistory' should influence the selection, but the core invocation context is covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds useful context about ladder ordering and brand-locking, but it does not materially expand on the meaning of 'userMessage' or 'recentHistory' beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('return') and resource ('the cheapest model on the ladder') and clearly defines the task: select the cheapest plausible model for a user message and provide reasoning. It is easy to distinguish from the sibling 'classify_turn' because the purpose centers on model selection, not classification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for when to use the tool: when a model ladder and a user message are available, and when BYOK provider constraints apply. It does not explicitly contrast with 'classify_turn' or state when not to use it, but the usage context is unambiguous enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv0.1.1
    • First observedclassify_turn
    • First observedrecommend_model
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 2 tools

Disambiguation3/5

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.

Naming Consistency5/5

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.

Tool Count3/5

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.

Completeness4/5

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

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • oracle-models

    vanppsa
    A
    license
    A
    quality
    D
    maintenance
    Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.
    3
    17 npm
    MIT

  • local-llm-delegation-mcp

    mrrodriguez
    A
    license
    A
    quality
    D
    maintenance
    Optimizes token costs by intelligently delegating low-complexity tasks to local LLMs via LiteLLM, enabling cost-effective development workflows.
    3
    1
    MIT

  • tokencast

    krulewis
    A
    license
    A
    quality
    C
    maintenance
    Pre-execution cost estimation for LLM agent workflows, providing cost estimates before running tasks and improving accuracy over time through calibration.
    6
    2
    MIT