Claude MarketplacesSubmit
ojaskord avatar

Local Model Suitability MCP

ojaskord/local-model-suitability-mcp

This is a cost optimization layer that sits between your agent and cloud LLM APIs. It exposes a single tool, check_local_viability, that evaluates whether a task can run on Ollama, LM Studio, or llama.cpp instead of paying for Claude or GPT calls. Pass it your prompt and quality threshold, and it returns a verdict with confidence level, recommended local models, and estimated savings. Useful if you're running high volumes of mixed complexity tasks and want to automatically route simple summarization or classification work to local 7B models while reserving cloud calls for complex reasoning. The routing logic itself runs on Claude Sonnet. Free tier gives you 20 decisions per month tracked by IP.

tool
1
transport
HTTP
last updated
Apr 13, 2026
View on GitHub

Tools

1 tools

Public tool metadata for what this MCP can expose to an agent.

check_local_viabilityCall 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`.

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`.

No parameter schema in public metadata yet.

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

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
AI & LLM Tools
Transport
HTTP

More from ojaskord

Related AI & LLM Tools MCP servers

View all
1oxgeneral avatarAgentNetoxgeneral/agentnetAgent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.0stars
2quartzunit avatarEmbgrepquartzunit/embgrepLocal semantic search — embedding-powered grep for files, zero external services.0stars
3rivradev avatarRecite MCPrivradev/recite-mcpLocal MCP server for Recite receipt processing with ledger and memory tools.0stars
4rjandino avatarZopafrjandino/zopafNegotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens.0stars
5rocnubie avatarMeigen AI MCProcnubie/meigenai-mcpMeigen AI is a curated meigen ai image prompt library.0stars
6rocnubie avatarNano Banana 2 MCProcnubie/nanobanana-2-mcpNano Banana 2 exposes the Nano Banana 2 image generation model online with prompt presets and quick0stars