Copilot Instructions for Ice Cream Topping Recommender MCPServer
## Project Overview
- This is a **demonstration repository** showcasing how to build MCPservers with elicitation capabilities.
- It's a minimal Model
116mo agoReviewMountCreate a free account to mount
asking the user
decision questions in ideation, architecture, or implementation,
query the `enterprise-standards-server` MCP for the Approved enterprise standards, policies, patterns
and ADRs that already constrain the work
free.** Put conversion/REST logic in `src/core/`, surfaced by both the CLI
(`src/cli/index.ts`) and the MCPserver (`src/mcp/server.ts`). Don't duplicate it into scripts.
- **Hand-rolled parsers on purpose** (glob, mini
other repositories.
It is not an agent framework, an orchestrator, or an MCPserver. No skill
requires an MCPserver.
## What to find, in priority order
1. **Correctness bugs
system, not a single assistant.
- `src/` is the Node.js/TypeScript control plane: Express API, MCPserver, CLI, dashboard backend, orchestration, hooks, and registries.
- `myai/` is the Python subsystem: FastAPI, FastMCP
RunWhen Platform MCPServer — Copilot Instructions
This repository provides an MCPserver for the RunWhen AI SRE platform.
Use the MCP tools to investigate infrastructure, build automation tasks,
and manage
Instructions
You have access to the user's Immich photo library through the immich-mcpserver: semantic CLIP search, OCR text-in-image search, albums, people/faces, libraries, upload and backup
onenote-mcp — Copilot Instructions
You have access to Microsoft OneNote via Microsoft Graph (12 tools: `onenote_*` + `authenticate` + `shutdown_server`).
**Before starting work:**
1. Find the notebook: `onenote_list_notebooks
JSONL
- AI-optimized CLI with JSON output
- Built-in daemon for background operations
- MCPserver integration for Claude and other AI assistants
**CRITICAL**: Use bd for ALL task tracking
111mo agoReviewMountCreate a free account to mount
multi-plugin marketplace** for Claude Code, distributing plugins
with commands, skills, agents, hooks, and MCP integrations. The architecture
uses:
- **Marketplace catalog** (`.claude-plugin/marketplace.json`) listing all
plugins
- **Plugin manifests** (`plugins
111mo agoReviewMountCreate a free account to mount
You are a senior Microsoft technical support escalation engineer, skilled in troubleshooting technical issues, architecture design, and solution design. Your role is to provide accurate, evidence-backed, and actionable guidance to customers and internal teams. You will leverage a variety of tools, including Microsoft Docs, Azure DevOps, and Kusto queries, to analyze issues and design solutions. Always follow the Problem-Solving Framework (Understand → Hypothesize → Investigate → Conclude → Recommend → Document) to ensure systematic and thorough responses.
name to switch to them.
The full squad is available via the Superteam MCPServer (see `.vscode/mcp.json`).
Any MCP-aware host can delegate to a specific agent with `superteam_delegate
open the database file until the first tool call requires it. This keeps the MCPserver startup instant and prevents lock contention during concurrent agent initializations.
2. **Prepared Statement Caching
Copilot Instructions
Harrier EMR MCP is a headless Python MCPserver for AWS DevOps Agent.
Follow the repository guidance in `AGENTS.md`.
Prefer existing project patterns:
- Runtime-specific behavior belongs under
Swagger2MCP Development Guide
## Project Overview
Swagger2MCP generates Model Context Protocol (MCP) servers from OpenAPI/Swagger schemas. The system uses a microservices architecture with separate frontend, backend API, background worker, Redis queue
111mo agoReviewMountCreate a free account to mount
Project Instructions
## Project: Devserver MCP
This project is a Model Context Protocol (MCP) server that manages development servers (Django, Vue, Celery, etc.) for LLM-assisted development workflows. Provides programmatic control