Skip to main content
Glama
deenesjakoruzh
VibeKit-Bot

Switchback MCP

by VibeKit-Bot
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Switchback MCP

MCP server for Switchback — 按复杂度对 AI 智能体回合进行分类，并选择能处理它们的最便宜模型。可直接用于 Claude Desktop、Cursor、Cline 以及任何 MCP 客户端。

npm Powers VibeKit

由 VibeKit 构建 — 与驱动我们托管产品中每个“Auto”回合的级联路由器相同。了解更多 →

功能

通过 Model Context Protocol 暴露两个工具：

  • classify_turn — 给定用户消息，返回 {tier: 0|1|2, why, fallback, durationMs}。当您决定是否在旗舰模型上花费，还是为下一个智能体步骤保留便宜模型时使用它。

  • recommend_model — 给定用户消息 + 模型阶梯（便宜 → 旗舰），返回阶梯上能合理处理它的最便宜模型。是 classify_turn 的便捷包装。

两个工具都通过 OpenRouter 发起一次小型模型调用（默认：openai/gpt-5.4-mini，约 $0.0001/次）。故障软降级：任何错误都返回 tier 1 且 fallback: true，而不是阻塞您的智能体。

Related MCP server: oracle-models

安装

npm install -g vibekit-switchback-mcp

配置

设置您的 OpenRouter 密钥（在 https://openrouter.ai/keys 获取）：

export OPENROUTER_API_KEY=sk-or-...

可选：覆盖分类器模型：

export SWITCHBACK_CLASSIFIER_MODEL=anthropic/claude-haiku-4.5

Claude Desktop

添加到您的 ~/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 / 其他

任何支持 stdio 服务器的 MCP 客户端。使用相同的 npx 调用。

示例调用

classify_turn:

{
  "userMessage": "rebuild the auth flow with passkeys"
}

返回：

{
  "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"
  ]
}

返回：

{
  "recommended_model": "openai/gpt-5.4-mini",
  "tier": 0,
  "ladder_size": 3,
  "classifier": { "tier": 0, "why": "trivial copy edit", "fallback": false, "durationMs": 318 }
}

何时使用

  • 多步智能体，可以在各轮之间切换模型。

  • BYOK 风格产品，希望将所有路由保留在用户选择的品牌内 — 为每个用户传递品牌锁定的阶梯。

  • 成本敏感的编排器，希望避免在琐碎回合上花费旗舰费率。

何时不要使用

  • 一次性聊天补全，无法在首次调用后更换模型 — 请改用 OpenRouter 的 auto 或 NotDiamond/Martian。

  • 延迟关键的 200ms 以下首 token 体验 — 分类器会增加 200-500ms。

许可证

MIT。参见 LICENSE。

由 VibeKit 构建。核心库是 vibekit-switchback — 本包是其 MCP 包装器。

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}.

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.

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
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

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
    36 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
    42 PyPI
    2
    MIT