MCP.so
登录

EVC Team Relay MCP

@entire-vc

代码仓库主页

关于 EVC Team Relay MCP

MCP server for reading and writing Obsidian vault documents via EVC Team Relay

#obsidian#mcp#collaboration#sync#notes#vault#crdt

基本信息

分类

记忆与知识

许可证

MIT

运行时

python

传输方式

stdio

发布者

entire-vc

提交者

Robert Johansson

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "evc-team-relay": {
      "command": "uvx",
      "args": [
        "evc-team-relay-mcp"
      ],
      "env": {
        "EVC_RELAY_URL": "https://your-relay.example.com",
        "EVC_RELAY_TOKEN": "your-token",
        "EVC_RELAY_SHARE": "your-share-id"
      }
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is EVC Team Relay MCP?

EVC Team Relay MCP gives AI agents read/write access to an Obsidian vault through the Team Relay API. It works with Claude Code, Codex CLI, OpenCode, and any MCP‑compatible client.

How to use EVC Team Relay MCP?

Install via uvx (recommended) or from source. Configure your AI tool’s MCP settings with a relay URL (RELAY_CP_URL) and either an agent key (RELAY_AGENT_KEY) or email/password. The server automatically authenticates and refreshes tokens. Once connected, agents can browse shares, list files, read, write, and delete files.

Key features of EVC Team Relay MCP

  • Read/write Obsidian vault files via Team Relay API.
  • No shell execution – all operations are Python function calls.
  • Automatic token management – agent never handles raw tokens.
  • Typed parameter validation against JSON Schema.
  • Supports stdio and HTTP (remote deployment) transports.
  • Compatible with Claude Code, Codex CLI, OpenCode, and other MCP clients.

Use cases of EVC Team Relay MCP

  • AI agent reads notes from an Obsidian vault for context.
  • Agent creates new notes or documents in a shared folder.
  • Agent updates existing files and changes appear in Obsidian instantly.
  • Securely integrate AI tools with a self‑hosted collaboration server.

FAQ from EVC Team Relay MCP

What prerequisites are needed?

Python 3.10+ with uv (recommended) or pip, a running EVC Team Relay instance, and a user account on the relay control plane.

How do I authenticate?

Use an agent key (recommended, supports read and write) or an email/password pair. Set RELAY_AGENT_KEY or RELAY_EMAIL/RELAY_PASSWORD in environment variables.

What transports are supported?

Stdio (default when using uvx) and streamable-http for remote deployment. HTTP mode requires running relay_mcp.py --transport http --port 8888 or using Docker Compose.

Where is data stored?

Data resides in the Obsidian vault. Team Relay stores documents as Yjs CRDTs and syncs them to Obsidian clients in real time. The MCP server reads and writes via Team Relay’s REST API.

How is security handled?

No CLI arguments; credentials are passed as environment variables. No shell execution – all calls are typed JSON‑RPC. Token lifecycle is managed internally; the agent never touches raw tokens.

评论

记忆与知识 分类下的更多 MCP 服务器

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

RAG Documentation MCP Server

hannesrudolph

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

267

Ultimate Google Docs & Drive MCP Server

a-bonus

The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.

605

Jupyter Notebook MCP Server (for Cursor)

jbeno

Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files

157

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425