Unified AI backend enabling OpenAI and Mistral with structured outputs, system prompts, and safety checks via Vercel AI SDK.

Fetches Datadog logs from Kubernetes clusters for Claude analysis with structured, contextual insights.

TypeScript-based integration with Google Tasks offering structured JSON task management, default list access, and full CRUD plus completion toggling.

A desktop AI app integrating multiple providers with context-aware workflows for chat, vision, and speech.

Security-hardened Chrome automation for AI agents with post-quantum encryption, tamper-evident audit logs, and SIEM-ready compliance.

Symbolic reasoning via Logic-LM using ASP and Clingo, integrates with Claude Code for natural-language to logical problem solving

Connects AI assistants to Lokalise, enabling automated localization workflows, bulk key operations, and multi-tool orchestration for fast content localization.

Xcode-based MCP server enabling AI assistants to create, build, test, and manage iOS/macOS projects with simulator controls.

MCP server for bare metal iKVM/IPMI console access — screenshot capture for LLM-based debugging

Extend Claude Code with custom commands, agents, hooks, Skills, and MCP servers through the plugin system.

MCP-one is a central server that connects multiple independent MCP servers and exposes a unified interface to clients (LLMs or applications).

Provides read-only access to Trading 212 data through a streamlined interface, exposing portfolios, instrument search, and historical data for AI assistants.

A Streamlit-powered Jira assistant with MCP integration. Create, search, and manage Jira tickets through a clean tabbed interface using natural language commands or direct forms. Built with Python and MCP framework.

A Model Context Protocol (MCP) server that provides AI assistants with access to Home Assistant, enabling smart home control and automation management.

Multi-layer AI agent enabling natural-language infrastructure management with BYOK, 45+ tools, and Kubernetes observability for secure, auditable multi-tenant deployments.

Dead-simple setup to expose your app's functions to AI agents, with quick Claude Desktop integration and simple tool definitions.

Lightweight MCP proxy that intercepts, transforms, and monitors tool calls via hooks and plugins without modifying existing server code.

Security-focused middleware for Model Context Protocol with JWT, PII checks, prompt-injection protection, rate limiting, and a visual dashboard.

Streamable HTTP MCP server template in Python with FastMCP, Docker/Devcontainer, and end-to-end testing.

Demonstrates cross-framework agent orchestration with tool access, multi-agent routing, and interactive web UI.

Lightweight CLI to discover MCP Servers via MCPRepository API, enabling quick, terminal-based server lookup and direct links.

Coordinated Claude 3.7 Sonnet swarm delivering coherent, ensemble-driven reasoning with multi-agent coordination.

Unified management for Deephaven sessions with live dataframes, AI-native integration, dynamic session creation, and enterprise-wide control.

Research-focused guide detailing Cursor AI integration with custom tools, practical code samples, and concrete implementation guidance.