Local Model Suitability MCP

io.github.OjasKordPublished by GitHub account OjasKordv1.1.23Updated Nov 2, 2026

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

The publisher's own server: model.tools — Zero-Auth Agent Utilities

VerifiedStreamable HTTPWeb executableDeveloper ToolsAI & ML

Overview

AI-generated overview

Tells an agent whether a task can run on a local model instead of a cloud API, returning a LOCAL or CLOUD verdict with cost-saving estimates.

What you can do
  • Check a task's suitability for local inference before a cloud call, with an optional quality threshold and data-sensitivity level.
  • Get back a verdict, confidence, reasoning, estimated per-call cost saving and suggested local models such as llama3.2 or mistral.
  • Force a LOCAL verdict for confidential data so it never leaves the machine.
When to use it
Useful when an agent makes many cloud inference calls and you want to cut spend by routing simple work to Ollama, LM Studio or llama.cpp. Also relevant when tasks may contain confidential data that should stay local.
Requirements
Runs as a remote HTTP endpoint or locally via npx (Node.js). The local package needs an ANTHROPIC_API_KEY for the Claude-based routing analysis; the README also shows an API_KEY for the paid tier. The free tier is tracked by IP and needs no key. Paid bundles are bought separately.
Before you install
The verdict comes from a paid third-party service that sends your task text to Anthropic Claude for analysis, so confidential task content may still leave your machine despite the LOCAL verdict. Free tier is limited to 20 calls per month and tracked by IP; paid bundles cost money. Treat verdicts as cost guidance only, not technical advice.

Installation

In SourceWeft

  1. Open Local Model Suitability MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.OjasKord%2Flocal-model-suitability-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "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:

FieldRequiredDescription
task✅The exact task you are about to send to a cloud model
quality_thresholdOptionalPRODUCTION (default) / PROTOTYPE / BEST_EFFORT
data_sensitivityOptionalPUBLIC (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"}

Data Sources

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

Pricing

PlanCallsPrice
Free20/month$0
Starter500-call bundle$20
Pro2,000-call bundle$70

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"      }    }  }}

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"    }  }}

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()

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"    })])

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

Source: README.md at commit 5e8da9c

Tools

1

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.

Parameterstaskrequireddata_sensitivityquality_threshold

Version history

1
  1. v1.1.23LatestSep 16, 2026

Score

100% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Model integrations

model.tools — Zero-Auth Agent Utilities

tools.modelOfficial publisher

Zero-auth remote utility server giving agents disposable email OTP reading, durable checkpoints, webhook bins, wake timers, receipts and page-to-Markdown…

Streamable HTTPWeb executable
Productivity & Workflow10 toolsOct 30, 2026

NLP.COM.AI Open Model Catalog

ai.com.nlpOfficial publisher

NLP.COM.AI Open Model Catalog's hosted MCP server, published by nlp.com.ai; no sign-in required; Streamable HTTP; 3 tools.

Streamable HTTPWeb executable
AI & ML3 toolsOct 25, 2026

Hologram Model Hub

foundation.uor.hubOfficial publisher

A remote MCP server that lets an assistant search an index of open models and get verified download links with SHA-256 checksums.

Streamable HTTPWeb executable
Files & Storage3 toolsOct 24, 2026

ModelLens

Published by GitHub account Greatbeing

Probes OpenAI-compatible model gateways, ranks models by measured latency and success, and recommends which model to use.

STDIODesktop only
Data & AnalyticsNot validated yetNov 7, 2026

Bedrock Multi-Model

Published by GitHub account Sagargupta16

Local MCP server that puts AWS Bedrock's text, image, video and embedding models behind nine tools so an assistant can ask, compare and judge models.

STDIODesktop only
Media & Design9 toolsNov 3, 2026