Local Model Suitability MCP

io.github.OjasKord由 GitHub 帳號 OjasKord 發布v1.1.23更新於 Nov 2, 2026

Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.

發布方自己的服務：model.tools — Zero-Auth Agent Utilities

已驗證Streamable HTTP可網頁執行開發者工具 AI 與機器學習

服務詳細資訊

識別碼: io.github.OjasKord/local-model-suitability-mcp
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 OjasKord。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.OjasKord%2Flocal-model-suitability-mcp.svg)](https://sourceweft.com/mcp/io.github.OjasKord%2Flocal-model-suitability-mcp?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

在呼叫雲端模型前判斷任務能否改由本機模型處理，回傳 LOCAL 或 CLOUD 結論與節省費用估算。

可以做什麼: 在送出雲端推論前檢查任務是否適合本機模型，可指定品質門檻與資料敏感等級。
取得結論、信心度、理由、每次呼叫預估節省的費用，以及建議的本機模型（如 llama3.2、mistral）。
對機密資料強制給出 LOCAL 結論，讓資料不離開本機。
適用情境: 適合代理大量呼叫雲端推論、想把簡單任務分流到 Ollama、LM Studio 或 llama.cpp 以降低支出的情境。也適用於任務可能含機密資料、需要留在本機處理的情況。
執行需求: 可作為遠端 HTTP 端點使用，也可透過 npx 在本機執行（需 Node.js）。本機套件需要 ANTHROPIC_API_KEY 進行 Claude 路由分析，README 另提到付費方案需 API_KEY。免費方案依 IP 計算、不需金鑰，付費方案須另行購買。

安裝前請注意

結論由第三方付費服務產生，任務文字會送往 Anthropic Claude 分析，因此即使結論為 LOCAL，機密內容仍可能離開本機。免費方案每月僅 20 次呼叫且依 IP 計算，付費方案需付費。結論僅供成本最佳化參考，不構成技術建議。

安裝

在 SourceWeft 中

開啟儀表板中的 Local Model Suitability MCP，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.OjasKord%2Flocal-model-suitability-mcp/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "local-model-suitability": {
      "type": "http",
      "url": "https://local-model-suitability-mcp-production.up.railway.app/"
    }
  }
}

README

[smithery badge]

Local Model Suitability MCP

[ToolRank]

Cloud inference is expensive. Everything that can run locally should.

This MCP server tells your agent — before every cloud API call — whether the task can be handled by a local model instead. Route to Ollama, LM Studio, or llama.cpp when you can. Only pay for cloud when you must.

The Tool

`check_local_viability`

Call this BEFORE every cloud inference call. If verdict is LOCAL, skip the cloud call entirely and route to your local model. Only use cloud when this tool returns CLOUD.

Inputs:

Field	Required	Description
`task`	✅	The exact task you are about to send to a cloud model
`quality_threshold`	Optional	`PRODUCTION` (default) / `PROTOTYPE` / `BEST_EFFORT`
`data_sensitivity`	Optional	`PUBLIC` (default) / `INTERNAL` / `CONFIDENTIAL`

CONFIDENTIAL forces LOCAL regardless of task complexity — data never leaves the machine.

Response:

json

{  "verdict": "LOCAL",  "confidence": "HIGH",  "reason": "Simple text summarisation — no reasoning depth required. Any 7B+ local model handles this well.",  "estimated_cost_saving": "$0.002-0.008 saved per call at claude-sonnet pricing",  "recommended_local_models": ["llama3.2:8b", "mistral-7b", "phi3:medium"],  "cloud_justified_reason": null,  "analysis_type": "AI-powered cost routing — NOT a simple lookup"}

{  "verdict": "LOCAL",  "confidence": "HIGH",  "reason": "Simple text summarisation — no reasoning depth required. Any 7B+ local model handles this well.",  "estimated_cost_saving": "$0.002-0.008 saved per call at claude-sonnet pricing",  "recommended_local_models": ["llama3.2:8b", "mistral-7b", "phi3:medium"],  "cloud_justified_reason": null,  "analysis_type": "AI-powered cost routing — NOT a simple lookup"}

Data Sources

AI reasoning: Anthropic Claude (claude-sonnet) — cost routing analysis
No external data sources — pure AI reasoning

Pricing

Subscribe at kordagencies.com

Setup

json

{  "mcpServers": {    "local-model-suitability": {      "command": "npx",      "args": ["-y", "local-model-suitability-mcp"],      "env": {        "ANTHROPIC_API_KEY": "your-key",        "API_KEY": "your-lms-api-key-for-paid-tier"      }    }  }}

{  "mcpServers": {    "local-model-suitability": {      "command": "npx",      "args": ["-y", "local-model-suitability-mcp"],      "env": {        "ANTHROPIC_API_KEY": "your-key",        "API_KEY": "your-lms-api-key-for-paid-tier"      }    }  }}

Free tier requires no API key — tracked by IP.

Harness Integration

Claude Code / Claude Desktop (.mcp.json)

json

{  "mcpServers": {    "local-model-suitability": {      "type": "http",      "url": "https://local-model-suitability-mcp-production.up.railway.app"    }  }}

{  "mcpServers": {    "local-model-suitability": {      "type": "http",      "url": "https://local-model-suitability-mcp-production.up.railway.app"    }  }}

LangChain (Python)

python

from langchain_mcp_adapters.client import MultiServerMCPClientclient = MultiServerMCPClient({    "local-model-suitability": {        "url": "https://local-model-suitability-mcp-production.up.railway.app",        "transport": "http"    }})tools = await client.get_tools()

from langchain_mcp_adapters.client import MultiServerMCPClientclient = MultiServerMCPClient({    "local-model-suitability": {        "url": "https://local-model-suitability-mcp-production.up.railway.app",        "transport": "http"    }})tools = await client.get_tools()

OpenAI Agents SDK (Python)

python

from agents import Agent, HostedMCPToolagent = Agent(    name="Assistant",    tools=[HostedMCPTool(tool_config={        "type": "mcp",        "server_label": "local-model-suitability",        "server_url": "https://local-model-suitability-mcp-production.up.railway.app",        "require_approval": "never"    })])

from agents import Agent, HostedMCPToolagent = Agent(    name="Assistant",    tools=[HostedMCPTool(tool_config={        "type": "mcp",        "server_label": "local-model-suitability",        "server_url": "https://local-model-suitability-mcp-production.up.railway.app",        "require_approval": "never"    })])

LangGraph

Same as LangChain above — langchain-mcp-adapters works with LangGraph natively.

Legal

Results are for cost-optimisation guidance only and do not constitute technical advice. Full terms: kordagencies.com/terms.html

來源：README.md，提交 5e8da9c

工具

check_local_viability

Checks whether a task can be handled by a local model instead of a cloud API. Call this BEFORE your agent routes any task to a cloud model — at the moment a task is ready to be sent and the model has not yet been selected. Use this when your agent is about to make a cloud inference call and wants to determine whether a local model could handle it at lower cost. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every routable inference call. Pass data_sensitivity=CONFIDENTIAL to force LOCAL verdict for tasks that must not leave the machine. Do not route to cloud without checking local viability first.

輸入參數task必填data_sensitivityquality_threshold