Claude MarketplacesSubmit
ojaskord avatar

Local Model Suitability MCP

ojaskord/local-model-suitability-mcp

Before you fire off another expensive Claude API call, this server asks whether a local model could handle it instead. It exposes a single tool, check_local_viability, that analyzes your task and returns LOCAL or CLOUD with reasoning, cost savings estimates, and recommended local models like llama3.2 or mistral-7b. If you mark data as CONFIDENTIAL, it forces local routing regardless of complexity. Works over stdio or HTTP, supports LangChain and OpenAI Agents SDK integrations. Free tier gives you 20 routing decisions per month, paid tiers unlock bundles. Think of it as a gatekeeper that saves you money by catching tasks that don't need Sonnet's firepower.

tool
1
auth
Secret needed
transport
STDIO, HTTP
env var
1
last updated
Jun 25, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://local-model-suitability-mcp-production.up.railway.app --name local-model-suitability-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http local-model-suitability-mcp https://local-model-suitability-mcp-production.up.railway.app

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 1 tools

Verified live against the running server on Nov 6, 2026.

check_local_viabilityChecks 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 infe...3 params

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 infe...

Parameters* required
data_sensitivitystring
CONFIDENTIAL forces LOCAL verdict regardless of task complexity — data must not leave the machine. Defaults to PUBLIC.one of PUBLIC · INTERNAL · CONFIDENTIAL
quality_thresholdstring
PRODUCTION = output quality matters and errors are costly. PROTOTYPE = approximate results acceptable. BEST_EFFORT = speed and cost trump quality. Defaults to PRODUCTION.one of PRODUCTION · PROTOTYPE · BEST_EFFORT
task*string
The exact task you are about to send to a cloud model. Be specific — include what the input is and what output you need.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Configuration

ANTHROPIC_API_KEY*secret

Anthropic API key for Claude routing analysis

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.

View the full README on GitHub

Details

Repository
github.com/ojaskord/local-model-suitability-mcp
Website
kordagencies.com
Category
Productivity & Office
Package
local-model-suitability-mcp
Transport
STDIO, HTTP
Auth
Required
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from ojaskord

Related Productivity & Office MCP servers

View all
1rusty4444 avatarShiori MCPrusty4444/shiori-mcpMCP server for Shiori bookmark management and tag workflows.0stars
2scaratec avatarTrelloscaratec/trellio-mcpMCP server for Trello — manage boards, lists, cards, attachments and more via Claude or Gemini0stars
3skyblue3925-svg avatarGeo Figure (지리 시험 지도·그래프)skyblue3925-svg/geo-figure-mcp지리 시험용 지도·그래프를 실제 통계로, 도형 하나하나 고칠 수 있는 PPTX·HWPX로 만든다.0stars
4srotzin avatarExecute Intentsrotzin/hive-executeIntent execution engine for autonomous agent task routing0stars
5standardbeagle avatarDart Querystandardbeagle/dart-queryDart AI task management MCP with batch operations, DartQL selectors, CSV import, zero context rot0stars
6tdavidson avatarHemrock MCPtdavidson/mcp-hemrockHemrock financial modeling prompts: context primers, task prompts, checks, and best practices.0stars