packages:
- **Root** (`/`) - Workspace orchestration, shared devDependencies
- **Server** (`/server`) - Express REST API on port 3001 + MCPserver on port 3002
- **Client** (`/client`) - React SPA on port 3000 (Vite dev server proxies
absolute workspace root path, not a subdirectory.
- **Server owners**: configure `--root /absolute/path/to/project` in your MCPserver args (or set `CORTEXAST_ROOT` env var). This is the most reliable
Copilot Instructions — garmin-grafana-mcp-server
## What this project is
This is a **Model Context Protocol (MCP) server** built with **FastMCP** in Python.
It reads Garmin health and training data
multi-repo workspace, hits carry `[scope/]`
labels; narrow with `--in /`. With the graft MCPserver connected, the
same tools are `graft_find_code`, `graft_find_all`, `graft_file_api`,
`graft
build
- Build subpackage: npm -w packages/dns-checks run build
- Run local Worker dev server: npx wrangler dev
- Run tests (Workers runtime): npm test
- Run subpackage tests: npm -w packages/dns-checks run test
verification.
- For code navigation (definitions, references, callers, impact): prefer the language-server (LSP) MCP tools first; only fall back to grep/find/read if the others are unavailable.
## VibeFlow commands (use these
GitHubCopilotOptions(model="gpt-5.5", timeout=settings.copilot_timeout_seconds, on_permission_request=_approve_all, mcp_servers={...})`. **Never** import `GitHubCopilotChatClient`, `ChatAgent`, or `MCPStreamableHTTPTool` — they do not exist in this repo's agent
Copilot Instructions — Purview DLM Diagnostics MCPServer
## MCP Tool Selection (Runtime Diagnostics)
When using the dlm-diagnostics MCPserver tools:
| User Intent | Tool | Examples |
|-------------|------|----------|
| Reports a problem or error
serve`) — the mirror image (server side:
HTTP in, stdio out): spawns a local stdio MCPserver as a child process
and publishes it as a Streamable HTTP endpoint so clients
LAIN — Codebase Intelligence
You have access to the Lain MCPserver (tool prefix `mcp__lain__`). Lain indexes
the current workspace and exposes tools for structural queries, semantic
search, and code
commands/ai-readiness-assess.md` nor
`skills/ai-readiness-assessment/SKILL.md` may reference, invoke, or
depend on any other plugin, skill, agent, MCPserver, or external
service. The `dependencies` field in `.claude-plugin/plugin.json` must
remain absent
DocuMCP AI Coding Agent Instructions
DocuMCP is an intelligent MCPserver for GitHub Pages documentation deployment with 45+ tools, Knowledge Graph memory system, and AST-based code analysis.
## Architecture Essentials
914mo agoReviewMountCreate a free account to mount
Global Instructions
## Project Context
This is Scholar Agent — a knowledge flywheel MCPserver with an academic paper research pipeline. It combines domain knowledge retrieval, structured research synthesis, and academic paper
Simple Memory MCPServer
TypeScript MCPserver for persistent memory storage with SQLite FTS5. Works as both MCPserver and CLI tool.
## Quick Reference
### Build & Test (All operations < 10 seconds
810mo agoReviewMountCreate a free account to mount
operation and defaults to `{}`.
- Never nest `cortex_act_batch_execute` inside itself.
- If `cortex_mcp_hot_reload` appears in a batch, it must be the final operation because it restarts
individual components.
- MCP automation is a first-class surface. `src/devtools/mcp-server.ts` starts the app’s MCPserver and registers tool groups from `src/devtools/tools/*`. The integration suites in `tests/suites/*` talk
server and client SDK for SignNow API integration, organized under `src/`.
- Major components:
- `sn_mcp_server/`: Main server logic, CLI, authentication, and tool integrations.
- `signnow_client/`: Handles SignNow API communication