requires one plugin skill, zero leaked client-extension
agents, and both non-empty portable MCPservers.
Claude Code 2.1.x rejects an `agents` field in plugin manifests. dotagents
therefore omits
Claude Code (claude.ai/code) when working with code in this repository.
## Project Overview
Penpot MCPServer is a Python-based Model Context Protocol (MCP) server that bridges AI language models
tests/run_tests.py --embeddings # Embedding tests only
python tests/run_tests.py --search # Search tests only
python tests/run_tests.py --mcp # MCPserver tests only
# Run tests with coverage
python tests/run_tests.py --coverage
# Run tests with verbose output
responds), Portal becomes the **read-only source of truth** for skills, knowledge, credentials, agents, MCPservers, and LLM providers. Do not add code paths that let the headless CLI write
files (`SKILL.md`) that teach the agent how to use the Python SDK, PAC CLI, MCPserver, and Dataverse Web API.
The plugin is loaded via:
```bash
claude --plugin-dir .github/plugins/dataverse
questions use the `navigator-research` agent.
Details: `skills/nav-deep-research/SKILL.md`.
### Code Intelligence (v7.5.0)
When a language-server plugin from the official marketplace is enabled (pyright-lsp,
typescript-lsp, gopls-lsp, …), `navigator-research
breaks the pattern.** It reads neither a flag nor a file
in the directory: MCPservers are declared by an installed PLUGIN (`server/agents/muse-mcp.ts`), and
`muse plugins install` records
Arkana Development Guide
## What is Arkana?
Arkana is a Model Context Protocol (MCP) server exposing 308 binary analysis tools to AI clients. It supports PE, ELF, and Mach-O formats
guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Project
MCPserver for Portainer, distributed on PyPI as `mcp-portainer`. The tool
surface is generated from
with the Anthropic SDK for demos, plus Python with FastMCP (managed by UV) for MCPserver implementations.
## Development Commands
```bash
# Install Node dependencies
npm install
# Verify environment setup
live runtime state, not a fixture
`data/memory.json` is the default storage file the memory MCPserver writes at runtime (`MCP_MEMORY_PATH` default in `segment_4_hero/memory_server/server.py`). It is **gitignored
talks to **Claude** and routes tool calls, prompts, and resources through one or more MCPservers spawned as stdio subprocesses. The bundled server (`mcp_server.py`) exposes an in-memory document store
mcp.json` (repo root) is the canonical demo target. Do **not** write a new MCPserver in this segment unless the learner specifically opts in to the optional homework. Point them
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.