Bond
Manage a Discord server in plain language, within the permissions of the member who signs in.
Hosted MCP Server
npx add-mcp 'https://mcp.bondbot.gg/mcp'Installs into Claude Code, Codex, Cursor and more
Documentation
Bond's MCP server for Discord
Bond's MCP server lets an AI app, such as Claude or ChatGPT, read your Discord server and make changes in it: create and edit channels, post and edit messages, schedule events, and build automations and slash commands. It acts as you, inside your own Discord permissions. You sign in with Discord. There is no API key.
Streamable HTTP, OAuth sign-in, tools only.
Server URL:
https://mcp.bondbot.gg/mcp
Connect an AI app
Bond has to be in the server first, and you have to be a member who can use it there. Then give your AI app the server URL.
Claude
- Open Connectors in Claude and add a custom connector. On a Team or Enterprise plan an owner adds it.
- Give it a name and paste the server URL.
- Connect, sign in with Discord, then approve the access it lists.
- Ask Claude to list your servers, and say which one to work in.
Anthropic's guide to custom connectors
ChatGPT
- Turn on developer mode in ChatGPT's settings. Not every plan or workspace has it.
- Add Bond as a custom MCP server and paste the server URL.
- Sign in with Discord, then approve the access it lists.
- Ask ChatGPT to list your servers, and say which one to work in.
OpenAI's guide to developer mode
Another MCP client
- It has to support remote servers with OAuth sign-in. The transport is streamable HTTP.
- Give it the server URL. Leave any API key field empty.
- The client opens the Discord sign-in. Approve the access it lists.
- Have it call
list_tools, thenlist_servers.
Claude and ChatGPT move their menus. These steps were read against each one's own guide on 2 Oct 2026.
What you approve at sign-in
The screen Bond shows, for an app that asked for every kind of access. You see the rows the app asked for.
-
Connect Claude to Bond
-
Sends access to claude.ai
-
Signed in as you. Not you?
-
Claude will be able to:
-
Read your servers: Channels, roles, members and messages you can already see
-
Make changes: Post messages, create and edit channels and threads, set up flows, commands and plugins, which can give out roles below yours
-
Delete things and change who can do what: Roles, channel permissions, kicks, bans, timeouts, verification level and automod. Anything that takes more with it still asks you first
-
Run Bond's own agent: Spends your token allowance
-
Claude can act in every Discord server you can act in. Bond checks your Discord permissions on every action, so it can never do more than you could by hand.
-
Approve, or Deny
-
It names the app and where your access goes: An app Bond does not recognise is marked Not verified.
-
Approve or Deny, as one set: There is no switch for each row. You approve everything the app asked for, or nothing.
-
It covers every server you can act in: You cannot limit an app to one server. Bond still checks your permissions in each server, on every call.
-
You sign in on mcp.bondbot.gg: You sign in with Discord there, even when you are already signed in to the dashboard. If you are still signed in there from an earlier connection, you go straight to this screen. Discord is asked for your identity and your server list, nothing else.
What an app can do
These are the server's own tools, read from its registry. list_tools returns the same list for your connection.
Start here
Not counted against your weekly calls.
list_tools: List every tool this connection can call, by category, with its class and whether it asks for a confirmation.list_servers: List the servers you can act in through Bond, with a handle for each.select_server: Check one server, and a channel if you name one, and get a handle to pass asserver.describe_tool: Get the full description, arguments and class of one tool, by its exact name.get_playbook: Get a tested recipe, step by step, for a common setup.get_more_results: Get the next page of a read whose result was cut short.
Read
Never changes anything. A result only holds what your Discord permissions already let you see, plus Bond's own data for that server.
read_memory: Read a saved note in full when it is relevant to a request.list_channels: List all channels in the Discord server: names, types (text, voice, category, forum, media, stage, announcement), IDs and parent category.list_roles: List all roles in the Discord server, sorted by position (highest position = most authority).get_role: Look up one role by ID or exact name, even one above Bond's own roles, and whether Bond can manage it.list_channel_permissions: Read every explicit permission overwrite on a channel or category, to audit its setup or copy it onto others.check_channel_access: Answer "who can actually see and do what here?" for many channels and subjects at once, the way Discord computes it.list_permission_changes: List the channel permission overwrites Bond itself changed, with the exact state each one had before the change.
Everything else, by name, through call_read_tool: Run any other read tool by name, with its arguments.
- Messages: 9 tools
- Members: 4 tools
- Moderation: 2 tools
- Threads & forums: 2 tools
- Emoji, stickers & soundboard: 3 tools
- Webhooks & integrations: 3 tools
- Scheduled events: 2 tools
- Automations & flows: 4 tools
- Custom slash commands: 3 tools
- Server settings: 12 tools
- Data & storage: 6 tools
- Voice: 2 tools
- Images & cards: 4 tools
- Plugins: 2 tools
- Paid roles: 2 tools
Change
Creates and edits.
save_memory: Save a lasting note about you or this server, so later conversations start with that context.create_channel: Create one text, voice, forum, media, stage, or announcement channel, optionally in a category, whose permissions it adopts. With permission overwrites it counts as destructive. Without them it is a plain change.bulk_create_channels: Create up to 20 channels of mixed types, such as text, voice, forum and stage, across existing categories in one step.edit_channel: Edit a channel's settings: name, topic (a forum's or media channel's Post Guidelines), slowmode, NSFW status, position, voice region or video quality, and thread defaults.set_slowmode: Set the slowmode (rate limit) on a text channel: members must wait this many seconds between messages.move_channel: Move a channel into a category, out of one, or to a different position in the channel list. Into a category it takes on the category's permissions by default, and that counts as destructive, as doessyncPermissions: truewith no position on a channel that stays in its category. PasssyncPermissions: falseto move it as a plain change.follow_channel: Follow an announcement channel so its published messages are crossposted into another channel automatically.clone_channel: Clone a channel: a new channel copying its type, topic, slowmode, NSFW status, and every permission overwrite, optionally under a different name.edit_forum_settings: Edit the defaults of a forum or media channel: reaction emoji, post sorting order, and whether every new post must have a tag.reorder_channels: Bulk update positions and parent categories for many channels, for coordinated layout changes that should land together. An entry withlockPermissions: truecounts as destructive: it takes on the permissions of the category it moves into, or the one it stays in.create_category: Create a category: a collapsible section in the channel list that groups related channels. With permission overwrites it counts as destructive. Without them it is a plain change.edit_category: Rename a category or change its position in the channel list.confirm_action: Pass your confirm or deny back to Bond. On confirm, Bond runs the action it was holding.ask_bond: Hand a job with several steps to Bond's own agent. It counts as one call and also spends tokens from your Bond allowance. A job never deletes or moderates.
Everything else, by name, through call_write_tool: Run any other change tool by name, with its arguments.
- Messages: 13 tools
- Members: 2 tools
- Moderation: 2 tools
- Threads & forums: 6 tools
- Emoji, stickers & soundboard: 6 tools
- Webhooks & integrations: 2 tools
- Scheduled events: 2 tools
- Automations & flows: 3 tools
- Custom slash commands: 2 tools
- Server settings: 6 tools
- Data & storage: 6 tools
- Voice: 7 tools
- Bulk operations: 1 tool
- Images & cards: 1 tool
- Plugins: 3 tools
- Paid roles: 2 tools
Delete, moderate and change who can do what
Deleting, kicking, banning, timeouts, roles, channel permissions, webhooks, automod and server security settings are a third class, reached through call_destructive_tool. Your app gets them only if you approved "Delete things and change who can do what" at sign-in. Without that, these tools are not in the list your app gets, and a call to one is refused. Nothing changes.
Without it, a flow, a custom command or a plugin an app saves can still give or take roles, when you have Manage Roles and every role is named in it and sits below your highest role. A direct role change needs the class.
An app you approved without that row can read and make ordinary changes. To allow this class, disconnect it under Connected apps on your account page, connect it again, and approve the row.
In this class: call_destructive_tool, delete_memory, delete_channel, delete_category, convert_channel_type, create_role, delete_role, assign_role, remove_role, set_member_roles, edit_role, reorder_roles, set_channel_permissions, reset_channel_permissions, apply_channel_access_policy, revert_permission_changes.
In this class too, by their arguments:
edit_scheduled_event: Cancelling or completing an event, which ends it for good.install_plugin: Installing a plugin whose flows or commands use a destructive tool.manage_forum_tags: Removing a forum tag.remove_reaction: Removing every member's reaction for one emoji.update_plugin: Updating a plugin whose flows or commands use a destructive tool.
No direct call for these: Sending a direct message, Web search, Reading your token usage, Image generation.
What waits for a person
A plain change gets no extra prompt from Bond. Your AI app's own approval of the call is the consent. Some actions do more than their arguments show. Those stop and wait for you.
- Bond holds the call. Nothing is written. The result says a confirmation is needed and carries a preview of exactly what Bond resolved.
- Your AI app shows you the preview. Word for word, as Bond wrote it.
- You confirm or deny. You answer in the app. Not in Discord, and not on bondbot.gg.
- The app sends your answer back. It calls
confirm_actionwith the preview unchanged. On confirm, Bond runs the held call itself. On deny, nothing happens.
Works once. Expires after 5 minutes. Same Discord account only. Refused if the target changed.
Always waits
- Deleting messages in bulk
- Running or reverting a bulk operation
- Banning members in bulk
- Pruning inactive members
- Uninstalling a plugin
- Selling a role, changing its price, or taking it off sale
- Undoing Bond's role edits
Waits when it does more than it says
- Deleting a category together with its channels
- Converting a channel when it has to be recreated, which loses its messages
- A permission change that lets @everyone or more members see or do more, or that would take away Bond's own access
- Changing @everyone's own server-wide permissions when it gives every member something new, or takes away View Channel, Send Messages or Connect. Any other role edit runs on your app's approval
- Saving a flow or a custom command that can delete, kick or ban
- Saving a flow that can DM members, which only the server owner can do
- Installing a plugin that can delete, kick, ban or DM members
- Installing or updating a plugin that opens data the server already stores to every member
- Updating a plugin so it can do more
- Turning on Bond answers first in Tickets for tickets it was off for, in a settings change, an install or an update
What that does and does not cover
- One named delete does not wait: Deleting one named channel, role, thread, message, flow or command, or kicking or banning one named member, runs on your AI app's own approval, with no Bond confirmation. Bond still resolves the target and checks your permissions twice.
- Your answer goes through your AI app: Bond cannot see your click. If you let the app run
confirm_actionwithout asking, nobody is asked. Keep that tool on ask every time. - There is no always allow: An Allow always you gave Bond in Discord does not count here, and nothing you approve here is remembered.
ask_bondstops at the same line: Inside a job Bond never deletes, kicks, bans, unbans, times out or lifts a timeout, prunes, purges messages, runs a bulk operation, opens a channel to @everyone, makes stored data public or removes a plugin. It stops and says so.
It can only do what you can do
Every call runs as the Discord member who signed in. There is no second set of permissions.
- Your permissions, checked twice: Each call is checked against your Discord permissions and your role position, before it starts and again just before it runs. A change reads your membership from Discord again first.
- You name the server: Every call that touches a server names it in
server: the server's id, or a handle fromselect_server. Bond never picks one for a change. - Four checks before anything runs: Bond is in the server. You are a member. The server's settings let you use Bond. There is a text channel you and Bond can both use.
- Some reads need a permission: Flows, custom commands, onboarding and widget settings need Manage Server. Webhooks need Manage Webhooks.
- Bond does not need Administrator: The install link on bondbot.gg leaves Administrator out. Without it, an app is also limited by Bond's own role: a channel that blocks Bond's role blocks the app too.
- A message it sends names you: A message sent by a direct tool call ends with a small requested by line with your name. It does not ping you, and it cannot ping @everyone or @here. Inside an
ask_bondjob, a message Bond writes itself has no such line, and it can ping @everyone only when your prompt asks for it and you hold Mention Everyone.
How Bond stays inside your permissions
Limits and cost
Tool calls are counted, not charged in tokens. How many you get in a week comes from your personal Bond plan.
Calls a week, by personal plan:
| Plan | Calls a week |
|---|---|
| Free | 100 |
| Pro | 2,000 |
| Max | 10,000 |
| Max 3x | 30,000 |
| Max 7x | 70,000 |
| Max 20x | 200,000 |
- The week: A rolling week for each Discord account, across every app you connect. It is not a calendar week. At the cap, the refusal says when the oldest call drops out.
- What counts: Every tool call, reads included, plus
confirm_actionandask_bond. A call that fails at Discord still counts. A call the cap refuses does not. - Not counted:
list_tools,list_servers,select_server,describe_tool,get_playbookandget_more_resultsdo not count. - Tokens: A direct tool call spends no tokens.
ask_bondcounts as one call and also spends tokens from your Bond allowance, the way a chat with Bond does. Its result says how many. - Safety limit: 60 calls a minute for each person, on everything, the tools that are not counted included. No plan raises it.
- Messages: One channel takes at most 10 messages sent this way in 10 minutes and 25 in an hour, counted across everyone who sends through Bond, and from at most 4 different people in an hour.
ask_bond: A prompt can be up to 8,000 characters. A job is cut off after about 90 seconds and can be continued with another call.
What Bond sees and keeps
- At sign-in: Discord tells Bond who you are and which servers you are in. Bond keeps that server list with the connection, so it knows which servers to check.
- For each call: A log row with your Discord id, the server, the tool's name, the app and the outcome. It holds no arguments, no results and no message text, and it is deleted after 30 days.
- For
ask_bond: The conversation is stored like a dashboard chat with Bond, with what Bond read to answer it. - Sign-in tokens: The tokens Bond gives your app are stored only as hashes. The app never gets your Discord token. The Discord sign-in itself creates a Bond session on mcp.bondbot.gg for 7 days, the same as a dashboard sign-in, and Bond holds Discord's token for it encrypted.
- What your AI app receives: Whatever a tool returns: what your Discord permissions already let you see, plus Bond's own data for that server. What the app does with it is under that app's own privacy policy.
- Message text: Bond holds Discord's Message Content intent. It uses the text of messages only when someone mentions Bond or replies to it, when an automation an admin built needs it, such as a keyword rule or a ticket transcript, when a member asks Bond to read a channel they can already open, or to answer in the help channels and tickets where an admin turned on its help desk or Bond answers first. A read of a channel through your app returns what its messages say. A member who ran
/opt-outshows up without their text, and the result says so.
For client builders and directory reviewers
- Endpoint:
https://mcp.bondbot.gg/mcp. One POST endpoint. GET and DELETE answer 405. - Transport: Streamable HTTP, stateless. It serves the 2026-07-28 MCP spec and older clients from the same endpoint. A batch request is refused with 400, and a body over 1 MB with 413.
- What it exposes: Tools only. No resources and no prompts. Every tool carries read-only and destructive hints, and Bond checks permissions on its own side whatever a client does with them.
- Sign-in: OAuth 2.1 authorization code with PKCE (S256), for public clients. A call without a token gets 401 with a
WWW-Authenticateheader that points at the OAuth metadata. A token that lacks a scope gets 403 naming every scope the call needs. - Client registration: Client ID Metadata Documents, or dynamic client registration. Loopback redirect URIs match on any port. The
resourceparameter has to be the endpoint URL. - Token lifetimes: An access token lasts 1 hour. A refresh token lasts 30 days and rotates. Using an old refresh token again ends the connection.
- State: Held in memory. Result pages last 15 minutes, a held confirmation 5 minutes and an idle session 30 minutes. A restart of Bond drops all three. A server handle is signed and lasts 1 day.
- Refusals:
insufficient_scopewhen a call needs a scope the connection was not granted, including a call whose arguments pick a destructive variant, or a flow, command or panel that would bind a destructive tool, on a connection withoutservers.destructive. A tool that needs a scope the connection lacks is not listed, and naming a tool through the wrongcall_*_toolreturnswrong_entry_point.confirmation_requiredis a status, not an error. 503 withRetry-Afterwhen the server is busy. - Scopes:
mcp(needed on every request),servers.read(the read tools),servers.write(the change tools andconfirm_action),servers.destructive(the destructive class, together withservers.write),agent(ask_bond, together withservers.write). A client that asks for none getsmcpandservers.read. - Discovery: Protected resource metadata, Authorization server metadata, Server card.
Questions about the MCP server
Is there an MCP server for managing a Discord server?
Yes. Bond runs a hosted MCP server for Discord at https://mcp.bondbot.gg/mcp. Add it to Claude, ChatGPT or another MCP client, sign in with Discord, and the app can read your server and make changes through Bond, each one checked against your own Discord permissions. On Bond's hosted server reads, changes and the destructive class are all on. Deleting channels, categories, roles, messages, threads, emojis, stickers, sounds, invites, events, stage instances, integrations, flows, commands, memories, stored documents and saved images, clearing all of a message's reactions, kicking, banning, timeouts and pruning, direct role and channel permission changes, AutoMod rules, webhooks, batch changes, converting a channel's type, ending polls, removing plugins, and server-wide settings such as verification, onboarding and the welcome screen need an app you approved for "Delete things and change who can do what" at sign-in.
Can I manage my Discord server from Claude or ChatGPT?
From Claude, yes: add Bond's MCP server as a custom connector, sign in with Discord, and Claude can read your server and make changes through Bond. ChatGPT takes custom MCP servers in developer mode, which not every plan or workspace has, and the steps on this page follow OpenAI's guide for it. Either way Bond has to be in the server, and every call is checked against your permissions there.
What's the best way to let an AI agent run my Discord server?
Give it a way to act that stays inside your own Discord permissions. Bond offers two. Mention Bond in Discord and its own agent does the work, showing a plan before it builds. Or connect your agent to Bond's MCP server and it calls Bond's tools as you, or hands Bond a job with several steps. Either way, Bond checks your permissions on every action.
Do I need an API key for Bond's MCP server?
No. There is no API key and no static token. Your AI app sends you to sign in with Discord, and Bond gives the app a token of its own.
Does Bond have to be in my server?
Yes. Bond has to be installed in the server, you have to be a member, and the server has to let you use Bond. A connected app cannot reach a server that Bond is not in.
Can I limit a connected app to one server?
No. The access you approve covers every server you can act in through Bond. Each call still names one server and is checked against your permissions there.
How do I disconnect an app?
Open the dashboard, go to your account and open Connected apps. Each app has its own Disconnect button, and the app's next call fails.
Can a connected app DM members or search the web?
Not with a direct tool call. A direct call cannot send a direct message, search the web or generate an image, and a message it sends cannot ping @everyone or @here. A flow that DMs members can only be saved by the server owner, and it waits for a confirmation first.
Bond has to be in the server first. Add it, then connect your AI app. Free to start.