db-mcp
neverinfamous/db-mcp/.github/copilot-instructions.md
Context Before starting work on this project, read `memory://briefing/db-mcp` from the `memory-journal-mcp` server for real-time context: - **Recent journal entries** — what was just worked
How real projects brief GitHub Copilot, from .github/copilot-instructions.md.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
neverinfamous/db-mcp/.github/copilot-instructions.md
Context Before starting work on this project, read `memory://briefing/db-mcp` from the `memory-journal-mcp` server for real-time context: - **Recent journal entries** — what was just worked
omgwtfwow/mcp-crawl4ai-ts/.github/copilot-instructions.md
BASE_URL` unset; fails fast if missing. Passes env + version into `Crawl4AIServer`. - `src/server.ts`: registers MCP tools, keeps a `Map<string, SessionInfo>` for persistent browser sessions, and uses `validateAndExecute` (Zod parse
zpratt/lousy-agents/.github/copilot-instructions.md
cases, gateways, and formatters cli/ Published CLI package and reference scaffold templates mcp/ Published MCP server package action/ Private GitHub Action package agent-shell/ Published npm script-shell telemetry package
alxpark/propresenter-mcp/.github/copilot-instructions.md
ProPresenter MCP Server Project ## Checklist - [x] Create copilot-instructions.md file in the .github directory - [ ] Get project setup information for MCP server - [ ] Create package.json with dependencies - [ ] Create TypeScript configuration - [ ] Create MCP server
Azure/multi-agent-doc-research/.github/copilot-instructions.md
Multi-Agent Collaboration → Response ├─ Web Search (Bing) ├─ AI Search (Azure AI Search) └─ YouTube Search (MCP Server) ``` ## Dual Orchestration Architectures ### 1. Agent Framework (`services_afw/`) - Production Pattern - **Pattern**: Executor-based workflow
bcgov/crow/.github/copilot-instructions.md
22codebase-memory-mcp%22%5D%7D). - If the codebase-memory-mcp server is available, use it and update the index as needed. Its scans are usually faster and cheaper than
fritzprix/libr-agent/.github/copilot-instructions.md
Think-Act-Observe loop managed entirely in Rust backend (`AgentSessionManager`) **MCP Integration Architecture:** - **External MCP Servers**: Stdio/HTTP protocol via `rmcp` library, managed by session-isolated managers - **Builtin MCP Servers**: Native
Looted/kibi/.github/copilot-instructions.md
workspaces under `packages/*`; the core engine is `packages/core`, the CLI `packages/cli`, the MCP server `packages/mcp`, and agent-host integrations `packages/{claude,codex,cursor,opencode,zcode,vscode}` ## Commands ```bash bun install
microsoft/entra-agentid-samples/n8n/.github/copilot-instructions.md
Azure Container Apps** with **Entra Agent ID** integration and a **Microsoft Graph MCP Server** connection, all from a single `azd provision` command. ### Deployment flow ``` azd provision ├─ Bicep (infra/main.bicep) → deploys
shrec/AIWorkHub/.github/copilot-instructions.md
hardcoded constant, and always leaves headroom so a scan cannot starve the interactive MCP server. - Parallelism changes only how fast, never what is measured or produced; results stay identical
tygryso/hypotree/.github/copilot-instructions.md
data-quality warnings) and the gate decision reference (criteria 1a/1b/2/3/4 with thresholds). ### hypotree@dev — MCP Server Agent Instructions **hypotree** is a persistent hypothesis-DAG orchestrator. It remembers what
Vasallo94/obsidian-mcp-server/.github/copilot-instructions.md
built with FastMCP that exposes Obsidian vault operations as tools, resources, and prompts. ``` obsidian-mcp-server/ ├── obsidian_mcp/ │ ├── server.py # Entry point - creates FastMCP instance and registers all modules │ ├── config.py # Pydantic
caiowilson/MCP-memento/.github/copilot-instructions.md
search`). ## Project architecture (big picture) - Entrypoint is [cmd/server/server.go](cmd/server/server.go#L1): `app.Run()` wires up the MCP server. - The MCP server lives in [internal/mcp/server.go](internal/mcp/server.go#L1): JSON-RPC over stdio, tool registry
dryvist/nix-ai/.github/copilot-instructions.md
Repository Purpose nix-ai is an AI CLI ecosystem (Claude Code, Antigravity, Codex, Copilot, MCP servers, MLX inference) delivered as Nix home-manager modules. It exports modules consumed
microsoft-foundry/build-2026-demos/agent-tools-and-integrations/toolbox-fibey-demo/.github/copilot-instructions.md
uvicorn fibey.gateway.api_server:app --reload --port 8080 # Agent CLI only uv run python -m fibey.agent.main # Frontend only cd ui && npm run dev # Inventory MCP cd services/inventory-mcp && uv sync
suryast/indonesia-civic-stack/.github/copilot-instructions.md
scraper.py` — fetch() and search() functions - `normalizer.py` — raw HTML/JSON → dict transformations - `router.py` — FastAPI routes - `server.py` — MCP server using CivicStackMCPBase - `app.py` — FastAPI app - `README.md` — module docs See `AGENTS.md` for full architecture guide
katalon-labs/true-skills/.github/copilot-instructions.md
project. - `true-platform-testing` - Route and run the full 7-stage testing lifecycle. ## Katalon MCP server These workflows depend on the Katalon MCP server. - **VS Code**: `.vscode/mcp.json` (included) defines
marktisham/LumosTrade/.github/copilot-instructions.md
LumosAI/Agents/LumosAgents/main.py` — agent entrypoint and ADK app. - `LumosAI/Tools/LumosDB/tools.yaml` — tool definitions for the toolbox. - `LumosAI/Tools/LumosTradeTool/src/index.ts` — Node MCP server entrypoint (Streamable HTTP at `/mcp`). - `shell/_invoker.sh` — authoritative list of environment launcher actions and their
realtydev/omada-mcp/.github/copilot-instructions.md
Omada MCP contributor automation Read `CONTRIBUTING.md` before changing code. It defines setup, required checks, tool additions, endpoint verification, and release procedure. Use `package.json`, `.nvmrc`, `tsconfig.json`, and `biome.json` for current tooling
bitflight-devops/mcp-json-yaml-toml/.github/copilot-instructions.md
Architecture ### Directory Structure ``` mcp-json-yaml-toml/ ├── packages/mcp_json_yaml_toml/ # Main package (ALL code here) │ ├── server.py # MCP server & tool implementations │ ├── yq_wrapper.py # Binary management & yq execution │ ├── schemas.py # Schema discovery & validation │ ├── lmql_constraints.py # LMQL constraint
Repository-wide instructions for GitHub Copilot, kept in .github/copilot-instructions.md.
How to build and test, the project's structure, and the conventions Copilot should follow in suggestions and reviews.
No. Copilot's coding agent also reads AGENTS.md, so many projects keep the shared rules there.
Open a file to see its discussion. Reports from people and their agents are coming.