The EVC Team Relay MCP Server gives AI agents secure read/write access to an Obsidian vault through the Team Relay API.
Authenticate — Log in to the Relay Control Plane via environment variables (
RELAY_CP_URL,RELAY_EMAIL,RELAY_PASSWORD); tokens are managed and refreshed automaticallyList Shares — Retrieve accessible shares with optional filtering by type (
docorfolder) and ownershipList Files — Browse all files within a specific folder share, returning a map of paths to document IDs and types
Read File — Read a file from a folder share by path (recommended high-level method for folder shares)
Read Document — Low-level access to read content directly by
doc_id, useful for doc shares or advanced use casesUpsert File — Create or update a file in a folder share, with automatic detection of whether to create or update
Write Document — Low-level write to replace a document's full content by
doc_id(intended for doc shares)Delete File — Remove a file from a folder share; deletion syncs to Obsidian on the next sync cycle
Enhanced security — No shell execution, validated inputs, and automatic token management
Broad compatibility — Works with Claude Code, Codex CLI, OpenCode, and any MCP-compatible client; supports remote deployment via HTTP transport
Allows AI agents to read from and write to an Obsidian vault, enabling capabilities such as listing files, reading document content, and creating or updating notes with real-time synchronization via the Team Relay API.
EVC Team Relay - MCP Server
Give your AI agent read/write access to your Obsidian vault.
Your agent reads your notes, creates new ones, and stays in sync — all through the Team Relay API.
Works with Claude Code, Codex CLI, OpenCode, and any MCP-compatible client.
Quick Start
1. Install
Option A — from PyPI (recommended):
No installation needed — uvx downloads and runs automatically. Skip to step 2.
Option B — from source:
git clone https://github.com/entire-vc/evc-team-relay-mcp.git
cd evc-team-relay-mcp
uv sync # or: pip install .2. Configure your AI tool
Add the MCP server to your tool's config with your Relay credentials.
Add to .mcp.json in your project root or ~/.claude/.mcp.json:
{
"mcpServers": {
"evc-relay": {
"command": "uvx",
"args": ["evc-team-relay-mcp"],
"env": {
"RELAY_CP_URL": "https://cp.yourdomain.com",
"RELAY_EMAIL": "agent@yourdomain.com",
"RELAY_PASSWORD": "your-password"
}
}
}
}Add to your codex.json:
{
"mcp_servers": {
"evc-relay": {
"type": "stdio",
"command": "uvx",
"args": ["evc-team-relay-mcp"],
"env": {
"RELAY_CP_URL": "https://cp.yourdomain.com",
"RELAY_EMAIL": "agent@yourdomain.com",
"RELAY_PASSWORD": "your-password"
}
}
}
}Add to opencode.json:
{
"mcpServers": {
"evc-relay": {
"command": "uvx",
"args": ["evc-team-relay-mcp"],
"env": {
"RELAY_CP_URL": "https://cp.yourdomain.com",
"RELAY_EMAIL": "agent@yourdomain.com",
"RELAY_PASSWORD": "your-password"
}
}
}
}If you installed from source instead of PyPI, replace "command": "uvx" / "args": ["evc-team-relay-mcp"] with:
"command": "uv",
"args": ["run", "--directory", "/path/to/evc-team-relay-mcp", "relay_mcp.py"]Ready-to-copy config templates are also in config/.
3. Use it
Your AI agent now has these tools:
Tool | Description |
| Authenticate with credentials (auto-managed) |
| List accessible shares (filter by kind, ownership) |
| List files in a folder share |
| Read a file by path from a folder share |
| Read document by doc_id (low-level) |
| Create or update a file by path |
| Write to a document by doc_id |
| Delete a file from a folder share |
Typical workflow: list_shares -> list_files -> read_file / upsert_file
Authentication is automatic — the server logs in and refreshes tokens internally.
Remote Deployment (HTTP Transport)
For shared or server-side deployments, run as an HTTP server:
# Direct
uv run relay_mcp.py --transport http --port 8888
# Docker
RELAY_CP_URL=https://cp.yourdomain.com \
RELAY_EMAIL=agent@yourdomain.com \
RELAY_PASSWORD=your-password \
docker compose up -dThen configure your MCP client to connect via HTTP:
{
"mcpServers": {
"evc-relay": {
"type": "streamable-http",
"url": "http://your-server:8888/mcp"
}
}
}Security
The MCP server provides significant security advantages over shell-based integrations:
No shell execution — all operations are Python function calls via JSON-RPC, eliminating command injection risks
No CLI arguments — credentials and tokens are never passed as process arguments (invisible in
psoutput)Automatic token management — the server handles login, JWT refresh, and token lifecycle internally; the agent never touches raw tokens
Typed inputs — all parameters are validated against JSON Schema before execution
Single persistent process — no per-call shell spawning, no environment leakage between invocations
Note: If you're using the OpenClaw skill (bash scripts), consider migrating to this MCP server for a more secure and maintainable integration.
How It Works
┌─────────────┐ MCP ┌──────────────┐ REST API ┌──────────────┐ Yjs CRDT ┌──────────────┐
│ AI Agent │ ◄────────────► │ MCP Server │ ◄─────────────► │ Team Relay │ ◄──────────────► │ Obsidian │
│ (any tool) │ stdio / HTTP │ (this repo) │ read/write │ Server │ real-time │ Client │
└─────────────┘ └──────────────┘ └──────────────┘ sync └──────────────┘The MCP server wraps Team Relay's REST API into standard MCP tools. Team Relay stores documents as Yjs CRDTs and syncs them to Obsidian clients in real-time. Changes made by the agent appear in Obsidian instantly — and vice versa.
Prerequisites
Python 3.10+ with uv (recommended) or pip
A running EVC Team Relay instance (self-hosted or hosted)
A user account on the Relay control plane
Part of the Entire VC Toolbox
Product | What it does | Link |
Team Relay | Self-hosted collaboration server | |
Team Relay Plugin | Obsidian plugin for Team Relay | |
Relay MCP | MCP server for AI agents | this repo |
OpenClaw Skill | OpenClaw agent skill (bash) | |
Local Sync | Vault <-> AI dev tools sync | |
Spark MCP | MCP server for AI workflow catalog |
Community
License
MIT