Marketplace

A 70B parameter Llama 3 model fine-tuned by Groq for function calling and tool use, optimized for structured JSON tool invocations with natural language understanding.

A specialized AI model for advanced tool use and function calling tasks, fine-tuned from Llama 3 8B with 89.06% accuracy on the Berkeley Function Calling Leaderboard.

Function calling with Llama 3 8B model optimized by Groq for structured tool/function invocation with JSON output

A Llama 3 8B model fine-tuned by Groq for function calling and tool use. Excels at API interactions, structured data manipulation, and complex tool execution with 89% accuracy on BFCL.

Quantized GGUF model for function calling and tool use based on Meta's Llama-3 8B, optimized by Groq. Available in multiple quantization levels for various hardware requirements.

Function calling and tool use with Llama 3 8B optimized for API interactions, structured data manipulation, and complex tool orchestration. Achieves 89% accuracy on Berkeley Function Calling Leaderboard.

Run the Llama-3-Groq-8B-Tool-Use model locally with GGUF quantization for function calling and tool use. Includes guidance on selecting optimal quantization for your hardware.

OAuth2-based CLI for accessing Jira, Confluence, and GitHub via MCP protocol. Provides tools for fetching issues, searching content, and managing repositories with Bearer Token authentication.

Generate a unified AI provider abstraction layer skill using the @auto-engineer/ai-gateway npm package for multi-provider AI integration with MCP tool support

Convert OpenAPI/Swagger specifications into Model Context Protocol (MCP) tool definitions with automatic parameter conflict resolution and HTTP request mapping.

Access OpenGraph.io API for link unfurling, HTML scraping, screenshot capture, and AI-powered image generation through MCP protocol

MCP server for interacting with Datadog API. Monitor incidents, logs, metrics, dashboards, traces, hosts, RUM, downtimes, and more through Claude.

Deploy and manage Railway infrastructure through your AI coding assistant. Create projects, deploy services, manage environments, configure variables, and monitor deployments with Railway's official MCP server.

Russian-optimized Gemma 2 9B model with strict function calling capabilities, fine-tuned with DPO for reliable tool use in conversational contexts. Available in GGUF format for efficient local inference.

Llama 3-based 8B model fine-tuned by Groq for function calling and tool use. Supports structured outputs and multi-turn conversations. Available in GGUF quantized formats for efficient local inference.

Angular 20 terminal/logging application using ng-terminal and @xterm/xterm libraries with standalone components architecture

IBM Granite 20B model optimized for function calling and tool use, quantized in GGUF format with imatrix weighting for efficient local deployment

Run Phi-4-mini-instruct with tool/function calling support using llama-server (llama-cpp-python). Provides ChatGPT-compatible API for LLM with external tool integration.

Manage Kubernetes clusters via kubectl and Helm - get resources, deploy applications, troubleshoot pods, manage nodes, and perform cluster operations with optional non-destructive mode for safe read-only access.

A lightweight Model Context Protocol (MCP) test server providing echo, debug, and greeting capabilities for testing MCP clients with predictable responses over STDIO or HTTP/SSE transports.