Omnicord

Omnicord is an MCP server that gives your AI assistant full operational control of a Discord server. Day to day chat, moderation, administration, and at the top end: building out an entire community server from a one paragraph brief.

You describe what you want. Your AI decides how to do it. Omnicord makes sure it happens correctly, and that nothing destructive happens without your say so.

How it works

Your AI client (Claude Desktop, Cursor, Windsurf, Claude Code, or any other MCP client) is the brain. Omnicord is the hands: it talks to Discord through your own bot, enforces Discord's rules before they bite, queues politely behind rate limits, and gates every destructive action behind a preview you confirm. There is no LLM inside Omnicord and no cloud service behind it. Your bot token stays in a file on your machine.

Quick start

You need Node 20 or newer and a Discord account. One command:

npx @orygn/omnicord init

Or from source:

git clone https://github.com/OrygnsCode/Omnicord.git && cd Omnicord
npm install
npm run build
node dist/index.js init

Prefer to watch? Here is the full setup, start to finish:

This walkthrough is a little dated now, but the core steps still apply. A fuller, updated walkthrough is planned.

The wizard goes from a bare Discord application to a working setup in about a minute. It takes the bot token with input hidden, verifies it live against Discord, checks the privileged intent toggles and waits while you fix any that are off, generates an invite link at the permission level you pick, saves the token locally (a gitignored .env for a source checkout, or .omnicord/.env in your user folder for an npx or global install), and writes the omnicord entry into your AI client's config (backing the file up first). Claude Desktop (including the Microsoft Store build), Cursor, Windsurf, and project level Claude Code are detected automatically, even before you have set up MCP in them; anything else gets a snippet to paste. It only adds the omnicord entry and never overwrites the rest of the file.

Then fully restart your AI client and ask it:

run a setup check on my Discord bot

Eight checks, plain English results, and the exact fix for anything that is wrong.

What it can do

Area	Examples
Server building	Plan and execute a full server build from a brief: roles, categories, channels, permissions, in one additive operation. Save, diff, and rebuild layouts as blueprints.
Messaging	Send, edit, pin, forward, react, polls, scheduled messages, DMs, webhooks.
Reading	Channel history, full-text message search, members, roles, permissions, audit log.
Moderation	Timeouts, kicks, bans, bulk actions, and prune, all preview first, plus raid lockdown to pause invites and DMs.
AutoMod	Discord's server side filters: keyword rules, Discord maintained preset lists (slurs, profanity), member profile checks, spam and mention flood limits.
Real time	Subscribe to live server events and ask "what did I miss?"
Structure	Channels, categories, permission overwrites, reordering, cloning, voice channel status.
Community	Events (one-off or recurring), stages, threads, forums, invites, welcome screen, onboarding.
Expression	Emojis, stickers, soundboard sounds.
Diagnostics	Setup check, bot info, rate limit status, permission explainers.

The full contract for every tool is in the tool catalog.

The safety model

Destructive operations (deleting, banning, kicking, timeouts, bulk actions) never execute on the first call. They return a human readable preview and a confirmation token bound to that exact action; repeating the call with the token executes it. Tokens are single use and expire after two minutes. Moderation additionally preflights Discord's hierarchy rules, owner protection, and self protection before the gate, so the failure mode is an explanation rather than a 403.

This is enforced by Omnicord itself, not by the model's judgment. A confused or compromised AI session cannot skip the gate.

Multiple bots

Omnicord can drive several bots from one install, one per server. Point it at a server and it uses the bot that is actually in that server, so a test bot and a real bot, or a separate bot per community, sit side by side without swapping tokens. Set it up by answering the wizard's "how many bots" prompt, or by hand in a bots.json. Destructive previews name the acting bot so a misrouted action is caught before it runs. A single DISCORD_TOKEN is unchanged and never sees any of this. Full details in Multiple bots.

Running it

Stdio, the default, for desktop MCP clients:

node dist/index.js

Streamable HTTP, for remote capable clients and self hosting:

node dist/index.js --http              # 127.0.0.1:3414/mcp
node dist/index.js --http --port 8080

A bot token sits behind the HTTP endpoint, so the defaults are strict: binding beyond localhost without OMNICORD_HTTP_TOKEN refuses to start, bearer auth is compared in constant time, browser origins are rejected unless allowlisted, and the Host header is validated in loopback mode to close DNS rebinding. Details in self-hosting.

Docker

A published image is on Docker Hub (orygn/omnicord), or you can build your own. The image runs the HTTP transport as a non root user with the container health check wired to the health endpoint. It binds beyond loopback, so it requires OMNICORD_HTTP_TOKEN and exits with a clear message without one. The token never lives in the image; everything arrives through the environment at runtime.

docker run -d -p 3414:3414 \
  -e DISCORD_TOKEN=your-bot-token \
  -e OMNICORD_HTTP_TOKEN=a-strong-secret \
  orygn/omnicord

To build it yourself instead: docker build -t omnicord .. Or with compose, after exporting the two secrets: docker compose up -d.

Configuration

Environment variables, or a .env file (the wizard writes one for you; source checkouts use .env next to package.json, npx and global installs use .omnicord/.env in your user folder). Multiple bots are configured in a bots.json in the same directory; see Multiple bots.

Variable	What it does
DISCORD_TOKEN	The bot token. Required for anything real; the server boots without it and the diagnostics explain what to fix.
OMNICORD_GUILD	Optional default server ID so tools can omit the guild parameter.
OMNICORD_SAFE_MODE	Default on. Destructive tools preview first and require a confirm token; set to false only for trusted automation.
OMNICORD_GATEWAY	Default on when a token is set: the bot shows as online and real time event subscriptions work. Set to off for REST only operation.
OMNICORD_HOME	Optional. One directory to hold .env, bots.json, and saved data. Defaults to the package root for a source checkout, .omnicord in your user folder for an installed copy.
OMNICORD_DATA_DIR	Where saved blueprints and scheduled messages live. Default: .omnicord next to package.json for a source checkout, .omnicord in your user folder for an installed copy.
OMNICORD_PORT	HTTP port, default 3414.
OMNICORD_HTTP_HOST	HTTP bind address, default 127.0.0.1.
OMNICORD_HTTP_TOKEN	Bearer token for HTTP mode. Required to bind beyond localhost.
OMNICORD_HTTP_ORIGINS	Comma separated browser origins allowed to call the HTTP endpoint. Empty means none.

Client config for stdio (Claude Desktop and compatible):

{
  "mcpServers": {
    "omnicord": {
      "command": "node",
      "args": ["/absolute/path/to/dist/index.js"]
    }
  }
}

No token goes in the client config. The server finds .env and bots.json no matter where the client spawns it from: it checks OMNICORD_HOME if set, then the current directory, then the package root, then .omnicord in your user folder, and a real environment variable overrides all of them.

Documentation

Doc	What is in it
Getting started	Setup in a few minutes, wizard or by hand.
Multiple bots	Running several bots, one per server, from one install.
Connecting AI clients	Exact config for Claude Desktop, Claude Code, Cursor, Windsurf, ChatGPT, and anything else.
Self-hosting	HTTP transport, Docker, and the security model for networked deployments.
Troubleshooting	Common problems and their fixes.
Security whitepaper	Plain language: what Omnicord can and cannot touch, for whoever decides whether to install it.
SECURITY.md	The engineering level threat model and audit findings.
Tool catalog	The full contract of all 151 tools.

The docs are written to be read by AI assistants too: paste a page at your AI and have it walk you through.

Omnicord is also listed on the official MCP registry, Smithery, and Docker Hub.

Tests

node scripts/unit.mjs        # pure logic: resolver, permissions, planner, gate
node scripts/smoke.mjs       # stdio protocol session, no token needed
node scripts/smoke-http.mjs  # HTTP transport, sessions, auth, security gates
node scripts/acceptance.mjs  # live end-to-end against a real test server

The acceptance suite needs DISCORD_TOKEN and OMNICORD_GUILD pointing at a disposable test server, and cleans up after itself. scripts/smoke-docker.mjs builds and verifies the container image and needs a running Docker daemon.

The unit and smoke suites need no Discord token, so you can watch the confirmation gate block a destructive call, and then let it through only with the token, before you trust this server with a bot of your own.

Contributing

Bug reports and pull requests are welcome. CONTRIBUTING.md covers the layout, the test suites, the conventions, and the one hard rule: any tool that deletes content, removes access, punishes a member, or fans a change out across many entities must go through the confirmation gate. The project follows the Contributor Covenant.

License

Omnicord is source available under the Elastic License 2.0. In plain terms: anyone may read, use, modify, and self host it freely, including businesses running their own communities. The one thing the license forbids is offering Omnicord to third parties as a hosted or managed service. The code is public so it can be audited; it is not up for resale as a service.

Versioning

Semantic versioning, tracked in CHANGELOG.md. 1.0.0 marked the public launch; releases since follow semver, and the npm badge above shows the current version. The version in package.json flows everywhere automatically: the MCP server identity, the health endpoint, and the wizard.

Built by Orygn LLC. Security reports: security@orygn.tech.