Results for “monte-carlo”

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data, covering correlation testing, available recipes, and multi-GPU examples.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Configure fault tolerance, straggler detection, preemption, in-process restart, and re-run state machine for Megatron Bridge training jobs.

Configure and validate CPU offloading for Megatron Bridge training, including activation offloading and optimizer state offloading with HybridDeviceOptimizer.

Generate a complete Rust Model Context Protocol server project with tools, prompts, resources, and tests using the official rmcp SDK.

Diagnose and fix connectivity issues with the Claude in Chrome MCP extension, including native host conflicts between Claude.app and Claude Code CLI.

Analyze investment portfolios by fetching real-time holdings via Alpaca MCP Server, then assess asset allocation, diversification, risk metrics, and generate rebalancing recommendations.

Analyze, describe, and extract information from images using the MiniMax vision MCP tool, with modes for general description, OCR, UI review, chart data extraction, and object detection.

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

Walk through the manual-capture.md checklist for a slug, driving Chrome via the Claude in Chrome MCP to capture each visual that needs more than a static URL — multi-step flows, conversation states, settings panels, age gates on third-party sites. Runs equally well locally (your desktop Chrome) or on a VPS with always-on Chrome + the extension installed. Defaults to unattended mode when `BLOG_AGENT_AUTONOMOUS=1` (which forces `UNATTENDED=1`). Use after /generate-visuals has flagged action-shot or failed-screenshot entries.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Build, test, inspect, install, and deploy MCP servers with FastMCP in Python, including wrapping APIs, databases, or files as tools and exposing resources or prompts.

MCP (Model Context Protocol) server configuration for Claude Code integration with trading platform. Trigger when setting up MCP servers, fixing alpaca-mcp-server issues, or adding new integrations.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Provides real-time structural code health scores via CodeScene MCP to review code quality before edits, verify score deltas after changes, and gate commits and PRs.

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

Read-only diagnostic that scans Claude Code session transcripts to surface which MCP servers and tools you actually use, ranked by call frequency, with zero-use servers flagged for removal. Use when planning an MCP cleanup, evaluating whether to keep a newly-added server, deciding which servers warrant token cost in the catalog, or before authoring an MCP-removal PR. Outputs a markdown report (last N days) — does not modify any settings. Pair with the manual `claude mcp remove <name>` step once findings are reviewed.

Set up MoonPay as an MCP server for Claude Desktop or Claude Code. Provides all MoonPay CLI tools via the Model Context Protocol.

Creating custom MCP tools for Claude

Connects MCP-compatible coding agents to Writingmate for model discovery, text comparison, image generation, and video generation using models like Seedance, Sora, Veo, Kling, and PixVerse.

Use for designing, creating, reviewing, or debugging Model Context Protocol server configuration for GitHub Copilot in Visual Studio Code, including .vscode/mcp.json, transports, inputs, trust, sandboxing, and tool scope. Do not use for implementing an MCP server, ordinary HTTP clients, or silently installing or starting external software.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Map and organize unwanted calls, texts, or emails after a U.S. senior-care referral inquiry by using GeezerKeeper's live public MCP for current network exit routes, separate provider jobs, unfilled request templates, duplicate-referral deadline facts, and current free or paid workflow fit. Use when a person asks why a senior-care marketplace or several providers are contacting them, how to opt out, how to prepare a stop-contact request, how to compare inquiry consequences before submitting a form, or how a senior-living professional should track direct-versus-network referrals. Do not use for emergencies, care placement, legal or medical advice, automatic sending, unknown-caller identity claims, or transmitting personal information.

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.