CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
ojaskord avatar

Local Model Suitability MCP

ojaskord/local-model-suitability-mcp
1 toolsauthSTDIO, HTTPregistry active
Summary

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.

Install to Claude Code

verified
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.

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

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

Tools

Verified live against the running server on Jun 10, 2026.

verified live1 tools
check_local_viabilityCall 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. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every r...3 params

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. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every r...

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.

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:

{
  "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

{
  "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)

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

LangChain (Python)

from langchain_mcp_adapters.client import MultiServerMCPClient
client = 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)

from agents import Agent, HostedMCPTool
agent = 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

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

Configuration

ANTHROPIC_API_KEY*secret

Anthropic API key for Claude routing analysis

Categories
Productivity & Office
Registryactive
Packagelocal-model-suitability-mcp
TransportSTDIO, HTTP
AuthRequired
Tools verifiedJun 10, 2026
UpdatedMay 2, 2026
View on GitHub

More from ojaskord

  • Quantum Suitability Validator
  • Tender MCP
  • VAT Validator MCP
  • URL Safety Validator MCP
  • Local Model Suitability MCP
  • Bizfile MCP
  • Data Compliance Classifier MCP
  • Document Integrity Validator
  • HS Code Classifier

Related Productivity & Office MCP Servers

View all →
omegamemory avatar
Omega

omegamemory/omega-memory

Maintain persistent project context by storing decisions, lessons, and task checkpoints for seamless session transitions. Navigate information through semantic search and relationship graphs to uncover related knowledge clusters. Automate memory consolidation and cleanup to keep your workspace organized and relevant.
omegamemory avatar
Omega

omegamemory/omega-memory-16ee60f9

Maintain persistent project context by storing decisions, lessons, and task checkpoints for seamless session transitions. Navigate information through semantic search and relationship graphs to uncover related knowledge clusters. Automate memory consolidation and cleanup to keep your workspace organized and relevant.
outlook avatar
Outlook

outlook

Read and send emails, manage calendar events, and organize contacts. Search messages, handle attachments, and schedule meetings.
peterliu1212 avatar
Codey 律所管理系統

peterliu1212/codey

Law firm management MCP: manage cases, clients, tasks, calendar and documents via Claude AI.
promptfax avatar
promptfax

promptfax/promptfax

PromptFax is a pay-per-use remote MCP server that lets an AI assistant send a real fax to a US fax number. Your assistant uploads a PDF or image, enters the destination, reviews a quote, opens Stripe Checkout, and queues the transmission. Pricing is $2.00 for the first 5 pages, then $0.10 per page after that, capped at $4.50 for up to 35 pages. Payment is captured only after the fax is recorded as delivered. There is no PromptFax account, no subscription, and no API key to manage. PromptFax uses OAuth and Streamable HTTP, so users install once and their assistant can start a fax workflow when needed. Inside ChatGPT, PromptFax opens a connector widget that handles document review, destination entry, Stripe Checkout, and the delivery report. Inside Claude or other MCP hosts, PromptFax falls back to an agent-friendly hosted session page that handles the same flow without requiring the host to pass files directly. Every real send requires a user-reviewed quote and Stripe authorization. The assistant cannot silently complete a fax. The `send_fax` and `cancel` tools are marked as destructive so well-behaved MCP hosts can surface confirmation steps. ## Capabilities - Send outbound faxes to US fax numbers - Attach a PDF or image from the host, widget, hosted session page, or HTTPS URL - Generate a pay-per-use quote before payment - Open Stripe Checkout for payment authorization - Queue a paid fax for transmission - Check workflow, payment, and delivery status - Retry eligible failed faxes - Cancel an active send while cancellation is still possible ## Tools - `start_session` — Create or resume a PromptFax MCP session. - `attach_document` — Bind a PromptFax document or HTTPS PDF URLs to an MCP session. - `get_quote` — Create a fax quote from a session, document, or HTTPS PDF URL. - `checkout` — Open Stripe Checkout after the user accepts a quote. - `send_fax` — Queue a paid fax for transmission. - `get_status` — Fetch workflow, payment, and transmission status. - `retry_failed_fax` — Prepare a retry flow after a retry-eligible failed fax. - `cancel` — Cancel the active send while cancellation is still possible. ## Common use cases - Sending a one-off medical record, referral, or intake form to a clinic's fax line. - Returning a signed contract to a small business or law office that still operates by fax. - Sending insurance claim forms, prior-authorization paperwork, or appeal letters. - Sending a benefits or HR form to a payroll vendor that requires fax submission. - Sending court filings or notarized documents to a filing office. ## Data handling PromptFax does not require an email address, does not provision a PromptFax account, and stores uploaded documents only as long as the fax workflow needs them. Server-side working copies are deleted after transmission. The browser-local delivery report persists for up to 24 hours unless cleared sooner. PromptFax is outbound-only and currently supports US fax numbers only. Payments are processed by Stripe for Cogint Labs LLC. ## Links - Homepage: https://promptfax.app/ - MCP endpoint: https://promptfax.app/mcp - Setup docs: https://promptfax.app/mcp-setup - Tool catalog: https://promptfax.app/mcp-tools - Demo: https://promptfax.app/mcp-demo - Pricing: https://promptfax.app/pricing - Privacy: https://promptfax.app/privacy - Terms: https://promptfax.app/terms
promptfax avatar
promptfax

promptfax/promptfax-d2a8bd34

PromptFax is a pay-per-use remote MCP server that lets an AI assistant send a real fax to a US fax number. Your assistant uploads a PDF or image, enters the destination, reviews a quote, opens Stripe Checkout, and queues the transmission. Pricing is $2.00 for the first 5 pages, then $0.10 per page after that, capped at $4.50 for up to 35 pages. Payment is captured only after the fax is recorded as delivered. There is no PromptFax account, no subscription, and no API key to manage. PromptFax uses OAuth and Streamable HTTP, so users install once and their assistant can start a fax workflow when needed. Inside ChatGPT, PromptFax opens a connector widget that handles document review, destination entry, Stripe Checkout, and the delivery report. Inside Claude or other MCP hosts, PromptFax falls back to an agent-friendly hosted session page that handles the same flow without requiring the host to pass files directly. Every real send requires a user-reviewed quote and Stripe authorization. The assistant cannot silently complete a fax. The `send_fax` and `cancel` tools are marked as destructive so well-behaved MCP hosts can surface confirmation steps. ## Capabilities - Send outbound faxes to US fax numbers - Attach a PDF or image from the host, widget, hosted session page, or HTTPS URL - Generate a pay-per-use quote before payment - Open Stripe Checkout for payment authorization - Queue a paid fax for transmission - Check workflow, payment, and delivery status - Retry eligible failed faxes - Cancel an active send while cancellation is still possible ## Tools - `start_session` — Create or resume a PromptFax MCP session. - `attach_document` — Bind a PromptFax document or HTTPS PDF URLs to an MCP session. - `get_quote` — Create a fax quote from a session, document, or HTTPS PDF URL. - `checkout` — Open Stripe Checkout after the user accepts a quote. - `send_fax` — Queue a paid fax for transmission. - `get_status` — Fetch workflow, payment, and transmission status. - `retry_failed_fax` — Prepare a retry flow after a retry-eligible failed fax. - `cancel` — Cancel the active send while cancellation is still possible. ## Common use cases - Sending a one-off medical record, referral, or intake form to a clinic's fax line. - Returning a signed contract to a small business or law office that still operates by fax. - Sending insurance claim forms, prior-authorization paperwork, or appeal letters. - Sending a benefits or HR form to a payroll vendor that requires fax submission. - Sending court filings or notarized documents to a filing office. ## Data handling PromptFax does not require an email address, does not provision a PromptFax account, and stores uploaded documents only as long as the fax workflow needs them. Server-side working copies are deleted after transmission. The browser-local delivery report persists for up to 24 hours unless cleared sooner. PromptFax is outbound-only and currently supports US fax numbers only. Payments are processed by Stripe for Cogint Labs LLC. ## Links - Homepage: https://promptfax.app/ - MCP endpoint: https://promptfax.app/mcp - Setup docs: https://promptfax.app/mcp-setup - Tool catalog: https://promptfax.app/mcp-tools - Demo: https://promptfax.app/mcp-demo - Pricing: https://promptfax.app/pricing - Privacy: https://promptfax.app/privacy - Terms: https://promptfax.app/terms