Source/WebSocket`
### Running Demos
Open `Demos/DemosVersion31.groupproj` in Delphi IDE to access all demo projects.
### Testing MCPServers
```bash
# Run demo server
AiMCPServerDemo.exe --protocol sse --port 8080
# Test via curl
curl
Delphi puro, sin `vec0`) y `TAiFunctions` con una función que dibuja series en TeeChart |
### MCPServers (03x)
| Demo | Purpose | Transport |
|------|---------|-----------|
| 031-MCPServer | Multi-protocol server. **Compila tambien en Linux64** desde
desde consumidores del framework
```
## Language
Documentation is primarily in **Spanish**. English versions available for:
- MCPServer (`MCPServer/uMakerAi-MCP.Server.EN.pdf`)
## Subdirectory CLAUDE.md Files
Specialized guidance exists in subdirectories:
- `Version 3/CLAUDE.md` - Full documentation
Project Purpose
MCPserver for Bear Notes, distributed through two channels:
- **MCP Bundle** (.mcpb) — a one-click installable extension for Claude Desktop. MCP Bundles are zip archives containing a local
SQLite reads** with **Zotero Web API writes**, and exposes the same surface via an MCPserver. The CLI follows an agent-native contract documented in `docs/agent-interface.md` (stable JSON envelope, typed
data/gos_workspace/skills_200_v1 --clear
```
### Auto-Discovery (Recommended)
The `.mcp.json` at the project root auto-registers the MCPserver. **Open the project directory in Claude Code** — the `graph-of-skills` server is immediately
calls `startTurn()` in **`lib/runner.ts`** and returns. The turn runs detached, owned by the server process: every event is persisted to SQLite and fanned out via **`lib/events.ts`** (in-process pub/sub keyed
jdocmunch-mcp
**Version:** 1.145.0 |
**Tests:** `PYTHONPATH=src python -m pytest tests/ -q`
⚠ **`python -m pytest`, not bare `pytest`**, matching the suite rule in
`C:\MCPs\CLAUDE.md`. The `-m` form guarantees
Claude.md - MCPServer Hello World
This file provides context about this project for AI assistants like Claude.
## Project Overview
This is a **Model Context Protocol (MCP) server** template built with
CLAUDE.MD
This document provides architectural context and implementation details for the Custom OpenAPI Spec MCPServer project. It's designed to help AI assistants understand the codebase structure, patterns
dies hard), per-session HTTP bridge (POST /eval →
`webContents.executeJavaScript`); extra env/command via
`userData/claude-env.json`, extra MCPservers via
`userData/claude-mcp.json`; `sweepStaleSessions()` clears leftovers of
hard-killed runs at startup.
Open and close
declarative AI agent environment manager written in Rust: a user declares skills, slash
commands, MCPservers, and instruction files in a `kasetto.yaml`, and `kst sync` pulls them from git
forges
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.