Enables AI assistants to interact with the Discord platform via a Model Context Protocol (MCP) server.
Discord Integration MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Enables AI assistants to interact with the Discord platform via a Model Context Protocol (MCP) server.
MCP-Discord provides the following Discord-related functionalities:
Once Discord Integration is connected, these are the calls the assistant has available:
discord_login — Login to Discord using the configured tokendiscord_list_servers — List all Discord servers the bot is a member ofdiscord_send — Send a message to a specified channeldiscord_get_server_info — Get Discord server informationdiscord_get_forum_channels — Get a list of forum channelsdiscord_create_forum_post — Create a forum postdiscord_get_forum_post — Get a forum postdiscord_list_forum_threads — List active and archived threads in a forum channeldiscord_reply_to_forum — Reply to a forum postdiscord_get_forum_tags — Get all available tags for a forum channeldiscord_set_forum_tags — Replace the available tags for a forum channeldiscord_update_forum_post — Update a forum post's title, tags, archived state, or locked stateBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
You will need one environment variable: DISCORD_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of team communication servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Discord Integration's toolset — discord_login, discord_list_servers, discord_send and 11 more — is a fair guide to whether it matches your workflow. It is maintained by barryyip0625; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| discord_login | Login to Discord using the configured token |
| discord_list_servers | List all Discord servers the bot is a member of |
| discord_send | Send a message to a specified channel |
| discord_get_server_info | Get Discord server information |
| discord_get_forum_channels | Get a list of forum channels |
| discord_create_forum_post | Create a forum post |
| discord_get_forum_post | Get a forum post |
| discord_list_forum_threads | List active and archived threads in a forum channel |
| discord_reply_to_forum | Reply to a forum post |
| discord_get_forum_tags | Get all available tags for a forum channel |
| discord_set_forum_tags | Replace the available tags for a forum channel |
| discord_update_forum_post | Update a forum post's title, tags, archived state, or locked state |
| discord_delete_forum_post | Delete a forum post |
| Cursor | This is the recommended setup for local command-based MCP clients. |
{
"mcpServers": {
"discord": {
"command": "node",
"args": [
"path/to/mcp-discord/build/index.js"
],
"env": {
"DISCORD_TOKEN": "your_discord_bot_token"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| DISCORD_TOKEN | Credential the server authenticates with. | Yes |
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Inbox intelligence — search, read, draft and send Gmail through your assistant with OAuth auto-setup.
Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Read and send Telegram messages through your assistant — chats, channels and history via the client API.
Enables Discord bot integration with Model Context Protocol (MCP) compatible applications like Claude Desktop.
Exposes REST APIs defined by OpenAPI specifications as Model Context Protocol (MCP) tools, facilitating seamless integration into MCP-based workflows.