mcp.json` (worktree sessions) → use the CLI twin:
`task_graph_cli.py --json`. Hermes operators: add the proposed `mcp_servers:` entry to
`~/.hermes/config.yaml`; Hermes walks up from its own working directory.
## Non-negotiable invariants
mcp.json` (worktree sessions) → use the CLI twin:
`task_graph_cli.py --json`. Hermes operators: add the proposed `mcp_servers:` entry to
`~/.hermes/config.yaml`; Hermes walks up from its own working directory.
## Non-negotiable invariants
summarize, not decide.
- Never execute, install, or connect to a scanned MCPserver.
- Never add default-on telemetry.
- Never weaken a detector, golden fixture, or corpus expectation to pass tests
Copilot instructions for forgekit
forgekit is a Node.js CLI (`forge`) + MCPserver: reliability infrastructure for AI
coding agents (evidence-linked memory, blast-radius analysis, guardrails, cost
governance). Zero runtime dependencies
ComparEdge MCPServer — Copilot Instructions
This repository contains the ComparEdge MCPserver (`@comparedge/mcp-server`).
## What this server does
Provides structured access to verified SaaS and AI tool data:
- Pricing plans
instructions apply whenever you are working in this repository or using the
**ie-mcp** MCPserver from any workspace.
---
## Automatic ie-mcp usage for tracked packages
If the user asks
code review — selenium-flow
## Purpose & scope
You are reviewing pull requests for a **Python MCPserver**: it drives a browser
on a remote Selenium Grid and exposes the same
maintained, fully-cited
personal wiki in Google's [Open Knowledge Format](../docs/okf-reference.md), with an MCPserver so an
AI can search and read it. It implements Karpathy's LLM-Wiki
Copilot Instructions for seq-mcp
This repository is dedicated to building a Dockerized MCPserver that provides AI agents (for example Codex and Copilot) with controlled access to Datalust
have access to opencode-cli-mcp: it orchestrates opencode agent runs, sessions, and system diagnostics through opencode serve.
**Before starting work:**
1. Check server status: opencode_system(action="status
GitHub Copilot Instructions
You are assisting on a TypeScript Model Context Protocol (MCP) server template project.
## Project goals
- Build a reliable, composable, production-minded MCPserver baseline.
- Keep the MCP
Mind Map MCP — Code Memory Engine (v1.4.0)
You have the AI Mind Map MCPserver connected. It is a persistent code memory system that eliminates redundant file re-reading
mcp]
# GitHub Copilot instructions — ssd-ai (byterover MCP)
**Elevator pitch:** A TypeScript/Node.js collection of MCPserver components and AI-assistant tools (memory, prompt, reasoning). Designed for testable, small utilities
311mo agoReviewMountCreate a free account to mount
blueprint)
- `.copilot/commands/pulse.md` → pipeline snapshot
- `.copilot/commands/focus.md` → move the active blueprint pointer
- `.copilot/commands/mcp-add.md` → add an MCPserver to .vscode/mcp.json
## Startup behavior (required)
1. Run the `survey` prompt first to create or refresh
Copilot Sync Instructions for AceDataCloud MCPs
## Repository Structure
This is a monorepo with one MCPserver per subdirectory (e.g., `suno/`, `luma/`, `flux/`).
Each subdirectory contains a standalone Python MCPserver
TypeScript compiler (`strict: true`) is the primary safety net.
## Architecture
amem is an MCPserver that gives AI coding tools persistent, searchable memory backed by SQLite. It communicates over stdio