this repository.
## Project Overview
This is an Obsidian plugin that implements MCP (Model Context Protocol) servers to enable Claude Code and Claude Desktop integration with Obsidian vaults. The plugin provides
files from various sources including local files, Git
repositories, GitHub/GitLab repos, web pages, and MCPservers.
## Development Commands
### Primary Commands
- `composer install` - Install dependencies
- `php ctx` or `./ctx
Read it
before making changes.
## What this project is
`concord-mcp` is a local MCPserver plus a `concord` CLI that gives coding agents
shared work-state: agents **register their
port to change)
- Both --cert and --key are required when using --https
> Note: MCPServers are typically launched by the Client as a subprocess.
## Code Style Guidelines
- **Imports
McpServerManager and LoopInterceptorManager.
- **factory.ts**: `createZypherAgent()` - simplified factory that creates
context, registers tools, and connects MCPservers in one call.
- **llm/**: Model provider abstraction (`ModelProvider` interface) with
implementations for Anthropic
Frontend (SvelteKit/Svelte 5)
```bash
cd frontend
npm install # Install dependencies
npm run dev # Dev server (port 5180)
npm run check # Type check
npm run lint # Lint
npm run format # Format
every block has deltas: some arrive complete in `content_block_start` (`redacted_thinking`, server-tool and MCP tool *results*, and new block types keep appearing), so default to passing whole
darknet-mcp — Dark Web Intelligence MCPServer
## Overview
66-tool MCPserver for dark web intelligence: breach data, ransomware tracking, Tor .onion access, malware analysis, blockchain intel, exploit search, stealer
BEFORE grep/find or reading files when you need to understand or locate code:
- **MCP tool** (when available): `codegraph_explore` answers most code questions in one call — the relevant symbols' verbatim
gold
This project uses OpenLore for persistent architectural memory.
Call `orient " "` (via the openlore MCPserver, or
`npx openlore orient --json`) **before touching a module you have not yet read
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.