How to connect Discord to OpenClaw

The ClawHub skill teaches OpenClaw about Discord, but the calls run through the ClawLink plugin and your connected account. Make sure Discord is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.

Reconnect Discord from the dashboard, then start a fresh chat if the runtime still has the old tool catalog loaded.

Discord tool schemas load on demand the first time a tool runs and are cached after that, so this error usually clears on its own: wait a few seconds and retry the same request. If every Discord call keeps failing with it in a fresh chat, reconnect from the dashboard, and contact support if it still persists — that pattern points to a configuration problem on our side, not something you can fix by reconnecting again.

Two usual causes. The connected account may not have access to the specific workspace, inbox, store, or project in the request — check that first. If access looks right, the agent may have sent a placeholder value (like "YOUR_ID" or an example id from documentation) instead of a real one: ask it to run a list or search tool first, then retry the action with a real id from those results. Most failures at this stage are one of these two, not ClawLink bugs.

This is Discord's rule, not a broken connection, and the tool descriptions state it outright. The application-command permission endpoints require an OAuth2 Bearer token from a user and reject bot tokens; other Discord endpoints do the reverse. On top of that, the authorizing user must hold MANAGE_GUILD and MANAGE_ROLES in the target guild for those specific calls, so an account without those roles gets an error even with a healthy connection. If the agent needs to act on a server rather than read your own membership, that is a signal to use the Discord Bot integration instead of trying to make this one reach further.

Ask the agent to diagnose it:

Call discord_get_my_user and discord_list_my_guilds, and tell me which account you are connected as and which servers it can see. Do not retry the failed call yet.

It is correct — there is no send-message tool in this integration, and the agent is not confused. The account-level Discord toolset covers identity, guild membership, connections, entitlements, and role connections. Message sending, channel reads, and moderation live in the Discord Bot integration, which registers the tools under a discordbot_ prefix. Connect that one from the dashboard and the tools appear in the next message. If the agent instead invents a plausible-looking name like discord_send_message, that name has never existed and the error will list the closest real tools.

Ask the agent to diagnose it:

List every Discord tool you actually have access to and tell me which of them can write anything. Do not guess at tool names.

Check which Discord account approved the grant. People routinely hold a personal account and one tied to a work or community identity, and the guild list the agent sees belongs to whichever account was signed in when you approved. The second cause is the consent screen itself: Discord lets you review what is being granted, and an approval that dropped the guilds permission leaves a connection that can identify you but cannot enumerate servers. Reconnect from the dashboard, confirm which account you are signing in as, and accept the full set.

Try reconnecting Discord and complete the consent flow in the same browser session. Partial OAuth approvals or switching accounts mid-flow can leave the connection incomplete.

Yes. ClawLink is the fastest way to connect OpenClaw to Discord: link your Discord account once in the browser and OpenClaw can call the Discord API through 27 ready-made tools — no custom code or token handling.

Paste the setup prompt from this page into OpenClaw. It installs the ClawLink Discord skill from ClawHub, then you click Connect in the dashboard to authorize Discord. OpenClaw calls the tools from the next message — no config files or API keys to manage.

About two minutes. Sign in, click Connect next to Discord in the dashboard, authenticate, and OpenClaw can use it from the next chat message.

The alternative to ClawLink is usually manual OAuth app setup plus your own token handling, permission troubleshooting, and tool plumbing for OpenClaw. That is fine if you want to build and maintain the integration yourself. Most teams just want Discord working from chat.

No, and it is worth being direct about it. This connection authorizes your Discord user account, and Discord's API does not let a user-scoped OAuth token post into channels the way a bot can. The tools here cover identity and membership: which servers you are in, your profile, your linked accounts, your role connections. To send messages, read channel history, or moderate, you want the Discord Bot integration, which is a separate connection with the guild, channel, and message tools. Connecting this one first and then wondering why the agent cannot post is the most common wrong turn on this provider.

They authenticate as different things. The Discord integration acts as you, through OAuth, and sees what your account can see. The Discord Bot integration acts as an application that has been added to a server, with the permissions that server granted it. Discord enforces the split at the API level — several endpoints accept a user OAuth token and explicitly reject a bot token, and the messaging endpoints work the other way round. Most agent use cases people describe as "connect Discord" are really the bot ones, so start there unless you specifically want the agent to reason about your own account and memberships.

Not for this connection. You approve access on Discord's own OAuth screen and the grant lives on the ClawLink server, so there is no application to register, no client secret, and no bot token to store. This is the part every search result gets differently: the standard walkthrough has you open the Developer Portal, create an application, add a bot user, enable privileged gateway intents, and copy the token into a config file. That is the self-hosted bot path. If you go the Discord Bot route through ClawLink, that registration is handled for you too.

The connection uses Discord's OAuth consent flow, so you approve a named set of permissions on Discord's screen, the agent never sees your password, and you can revoke the grant from the ClawLink dashboard or from Discord's authorized-apps settings at any point. The scope of risk on this particular integration is narrow by construction, because the account-level toolset is mostly read-only — it can tell the agent which servers you are in, not act inside them. The integration to think harder about is the bot one, where the permissions you grant on a server are what the agent can do there.

The ClawHub skill teaches OpenClaw about Discord, but the calls run through the ClawLink plugin and your connected account. Make sure Discord is connected in the dashboard, then start a fresh chat so OpenClaw reloads the tool catalog. If OpenClaw runs as a persistent gateway, restart it so the new tools register.