Provides full administrative control over Discord communities, enabling management of messages, moderation actions like kicking and banning, channel and role configuration, member management, and scheduled events.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Discord MCP Server Create a new #announcements channel and post a welcome message there"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides full administrative control over Discord communities. Enables AI assistants like Claude to manage Discord servers through 128 operations covering messages, moderation, channels, roles, events, and more.
Messages: Send, read, edit, delete, pin messages and manage reactions
Moderation: Kick, ban, timeout members with audit log support
Channels: Create, edit, delete channels with permission management
Threads: Create and manage threads and forum posts
Roles: Full role CRUD with permission configuration
Members: List, search, edit members and manage their roles
Events: Create and manage scheduled events
Polls: Create polls with multiple choice options
Webhooks: Create and send messages via webhooks
AutoMod: Configure auto-moderation rules
Voice: Move and disconnect members from voice channels
And more: Emojis, stickers, invites, templates, onboarding, stage channels...
Related MCP server: discord-mcp
Python 3.12+
uv package manager
A Discord account
A Discord server where you have admin permissions
This makes the discord-mcp command available system-wide:
git clone https://github.com/glittercowboy/discord-mcp.git
cd discord-mcp
uv tool install -e .You can also use pipx install -e . if you prefer pipx over uv.
Clone and run directly without installing:
git clone https://github.com/glittercowboy/discord-mcp.git
cd discord-mcp
uv syncFollow these steps carefully to create and configure your Discord bot.
Go to the Discord Developer Portal
Log in with your Discord account
Click the "New Application" button (top right)
Enter a name for your application (e.g., "My MCP Bot")
Accept the Terms of Service and click "Create"
In your application's settings, click "Bot" in the left sidebar
Click "Add Bot" and confirm by clicking "Yes, do it!"
Your bot is now created!
IMPORTANT: Your bot token is like a password. Never share it or commit it to version control.
In the Bot section, find the "Token" area
Click "Reset Token" (or "Copy" if available)
You may need to enter your Discord password or 2FA code
Copy the token immediately - you can only see it once!
Store it somewhere safe (you'll need it for configuration)
If you lose your token, you'll need to reset it, which invalidates the old one.
Still in the Bot section, scroll down to "Privileged Gateway Intents" and enable:
Intent | Why It's Needed |
Server Members Intent | Required for listing members, managing roles, and member-related operations |
Message Content Intent | Required for reading message content (not just metadata) |
Click "Save Changes" at the bottom.
Click "OAuth2" in the left sidebar
Click "URL Generator" under OAuth2
Select these scopes:
bot
applications.commands
Select bot permissions:
For full functionality, select "Administrator".
Or for minimal permissions, select these individually:
Manage Channels
Manage Roles
Kick Members
Ban Members
Manage Messages
Read Message History
Send Messages
Create Public Threads
Create Private Threads
Manage Threads
Embed Links
Attach Files
Add Reactions
Use External Emojis
Manage Webhooks
View Audit Log
Moderate Members (for timeouts)
Manage Events
Create Events
Send Polls
Copy the generated URL at the bottom of the page
Open the URL you copied in your browser
Select the server you want to add the bot to (you need "Manage Server" permission)
Review the permissions and click "Authorize"
Complete any CAPTCHA if prompted
The bot should now appear in your server's member list (it will show as offline until the MCP server runs)
Open Discord (desktop app or web)
Go to User Settings (gear icon near your username)
Navigate to App Settings > Advanced
Enable "Developer Mode"
Close settings
Right-click on your server name in the server list
Click "Copy Server ID"
Save this ID - you'll need it for configuration
You need two values:
Bot Token (from Step 3)
Server ID (from Step 7)
Depending on your installation method:
Method | Command |
Editable install ( |
|
Run from directory |
|
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"discord": {
"command": "uv",
"args": ["--directory", "/path/to/discord-mcp", "run", "python", "-m", "src.server"],
"env": {
"DISCORD_BOT_TOKEN": "your-bot-token-here",
"DISCORD_GUILD_ID": "your-server-id-here"
}
}
}
}Tip: If you used
uv tool install -e ., you can simplify to just"command": "discord-mcp"with noargs.
Add to .claude/settings.json or via claude mcp add:
{
"mcpServers": {
"discord": {
"command": "uv",
"args": ["--directory", "/path/to/discord-mcp", "run", "python", "-m", "src.server"],
"env": {
"DISCORD_BOT_TOKEN": "your-bot-token-here",
"DISCORD_GUILD_ID": "your-server-id-here"
}
}
}
}Tip: If you used
uv tool install -e ., you can simplify to just"command": "discord-mcp"with noargs.
Add to ~/.config/opencode/opencode.json:
{
"mcp": {
"discord": {
"type": "local",
"command": ["discord-mcp"],
"environment": {
"DISCORD_BOT_TOKEN": "your-bot-token-here",
"DISCORD_GUILD_ID": "your-server-id-here"
},
"enabled": true
}
}
}Optional: Add a Discord agent for auto-allowed permissions (press Tab to switch):
{
"agent": {
"Discord": {
"mode": "primary",
"permission": { "discord_*": "allow" }
}
}
}After configuration, restart your MCP client (Claude Desktop, Claude Code, or OpenCode) and try:
Ask Claude to discover available Discord operations
Ask Claude to list channels in your server
Ask Claude to send a test message to a channel
If you see errors:
Double-check your bot token is correct
Verify the bot is in your server
Ensure privileged intents are enabled in Developer Portal
Once configured, Claude can interact with your Discord server using these tools:
discord_discoverBrowse all available operations organized by category.
discord_get_schemaGet detailed parameter schema for a specific operation.
discord_get_schema("messages.send")discord_executeExecute an operation with parameters.
discord_execute("messages.send", {
"channel_id": "123456789",
"content": "Hello from Claude!"
})Category | Operations | Description |
messages | 9 | Send, read, edit, delete, pin messages |
reactions | 5 | Add, remove, list reactions |
threads | 10 | Create, manage, archive threads |
channels | 7 | Create, edit, delete channels |
members | 6 | List, search, edit members |
moderation | 7 | Kick, ban, timeout members |
roles | 5 | Create, edit, delete roles |
invites | 4 | Create, list, delete invites |
events | 6 | Scheduled event management |
polls | 2 | Create and end polls |
guild | 4 | Server settings and info |
audit_log | 1 | View audit log |
automod | 5 | Auto-moderation rules |
webhooks | 7 | Webhook management |
voice | 2 | Voice channel controls |
emojis | 5 | Custom emoji management |
stickers | 3 | Sticker management |
forum | 5 | Forum posts and tags |
stage | 6 | Stage channel instances |
onboarding | 3 | New member onboarding |
welcome_screen | 2 | Welcome screen settings |
soundboard | 5 | Soundboard sounds |
commands | 5 | Slash command management |
integrations | 2 | Server integrations |
widget | 3 | Server widget |
vanity | 2 | Vanity URL |
templates | 6 | Server templates |
dm | 1 | Direct messages |
bulk_ban | 1 | Bulk ban users |
discord_execute("messages.send", {
"channel_id": "1234567890",
"content": "Hello, Discord!"
})discord_execute("polls.create", {
"channel_id": "1234567890",
"question": "What's your favorite color?",
"answers": ["Red", "Blue", "Green"],
"duration_hours": 24
})discord_execute("moderation.timeout", {
"user_id": "9876543210",
"duration_seconds": 3600,
"reason": "Breaking server rules"
})discord_execute("events.create", {
"name": "Community Meetup",
"description": "Weekly community call",
"start_time": "2025-01-25T18:00:00Z",
"location": "https://meet.example.com"
})Never commit your bot token to version control
Never share your bot token publicly
If your token is exposed, reset it immediately in the Developer Portal
Use environment variables for sensitive configuration
Grant only the permissions your bot actually needs
The bot can only manage resources below its highest role in the hierarchy
Review Discord's Bot Best Practices
Discord enforces rate limits on API requests. This server handles rate limiting automatically, but be aware:
Global limit: 50 requests/second
Per-route limits vary by endpoint
Bulk operations are more efficient than individual calls
Your bot token is incorrect or has been reset
Get a new token from the Developer Portal
The bot lacks required permissions
The bot's role is too low in the hierarchy to manage the target
Check channel-specific permission overrides
The MCP server only connects when Claude makes requests (REST API, not Gateway)
This is normal - the bot doesn't maintain a persistent connection
Enable "Message Content Intent" in the Developer Portal Bot section
This is required to read the text content of messages
Enable "Server Members Intent" in the Developer Portal Bot section
This is required for member-related operations
The bot's highest role must be above the target user's highest role
Bots cannot manage the server owner
Check if there are channel-specific permission denies
MIT License - see LICENSE for details.
Browse all available Discord operations organized by category.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'browses' operations, implying a read-only action, but doesn't clarify if it's safe, requires authentication, has rate limits, or what the browsing entails. For a tool with zero annotation coverage, this is a significant gap in behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence: 'Browse all available Discord operations organized by category.' It is front-loaded with the core purpose, has zero waste, and is appropriately sized for a simple tool. Every word earns its place, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no annotations, but with an output schema), the description is minimally adequate. It states what the tool does but lacks details on behavior, usage context, or output interpretation. The presence of an output schema reduces the need to explain return values, but more context could help the agent understand when and how to use this tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description doesn't need to add parameter semantics, and it appropriately doesn't mention any. A baseline score of 4 is applied since no parameters exist, and the description doesn't introduce confusion.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Browse all available Discord operations organized by category.' It specifies the verb ('browse') and resource ('Discord operations'), though it doesn't explicitly differentiate from siblings like discord_execute or discord_get_schema. The purpose is clear but lacks sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose discord_discover over discord_execute or discord_get_schema, nor does it provide context about prerequisites or typical use cases. This leaves the agent without explicit usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a Discord operation with specified parameters.
Args:
operation: Operation identifier (e.g., 'messages.send', 'members.list') or 'batch.category.action' for batch operations
params: Operation parameters (get schema first)
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | ||
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions executing operations and referencing a schema, but fails to describe critical traits such as required permissions, rate limits, side effects (e.g., whether it's read-only or mutative), or error handling. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with a clear opening sentence followed by brief parameter explanations. It avoids unnecessary verbosity, though the 'get schema first' note could be more integrated. Overall, it is efficient with minimal waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (2 parameters with nested objects, no annotations, but an output schema exists), the description is moderately complete. It covers basic purpose and parameter hints, and the presence of an output schema reduces the need to explain return values. However, it lacks sufficient detail on behavior and usage, making it adequate but with clear gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds some meaning by explaining 'operation' as an identifier with examples and 'params' as operation parameters with a note to 'get schema first,' but this is insufficient for two parameters with nested objects and no schema details. The description does not fully clarify parameter usage or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'Execute[s] a Discord operation with specified parameters,' which is a tautology of the tool name 'discord_execute' and provides minimal specificity. It mentions operation identifiers like 'messages.send' or 'members.list' but does not clearly distinguish what this tool does versus its siblings (e.g., discord_discover, discord_get_schema), leaving the purpose vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit guidance on when to use this tool versus alternatives. The mention to 'get schema first' for params implies a prerequisite but does not specify when to choose discord_execute over discord_discover or discord_get_schema, nor does it provide context for its application, resulting in minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed parameter schema for a specific operation.
Args:
operation: Operation identifier (e.g., 'messages.send', 'members.list') or 'batch.category.action' for batch operations (e.g., 'batch.members.add_role')
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool does but doesn't cover key aspects like whether it's a read-only operation, potential rate limits, error handling, or the format of the output (though output schema exists). This leaves gaps in understanding how the tool behaves beyond its basic function.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded: the first sentence clearly states the purpose, followed by a structured 'Args' section with bullet points. Every sentence earns its place by providing essential information without redundancy, making it efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter) and the presence of an output schema (which handles return values), the description is largely complete. It covers the purpose and parameter semantics adequately. However, it could improve by addressing behavioral aspects like read-only nature or error cases, which are not fully covered by the output schema alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds significant meaning beyond the input schema, which has 0% description coverage. It explains that the 'operation' parameter is an identifier and provides concrete examples (e.g., 'messages.send', 'batch.category.action'), clarifying its semantics. This compensates well for the schema's lack of details, though it doesn't cover all possible edge cases or formats.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Get detailed parameter schema for a specific operation.' It specifies the verb ('Get') and resource ('parameter schema'), making it understandable. However, it doesn't explicitly differentiate from sibling tools like 'discord_discover' or 'discord_execute', which might also involve schema-related operations, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by mentioning 'specific operation' and providing examples of operation identifiers, suggesting it should be used when schema details are needed. However, it lacks explicit guidance on when to choose this tool over alternatives like 'discord_discover' (which might list operations) or 'discord_execute' (which might use the schema), leaving the context somewhat vague.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0discord_discoverdiscord_executediscord_get_schemaScored across 3 tools
The three tools have clearly distinct purposes: discover for browsing operations, execute for performing actions, and get_schema for retrieving parameter details. There is no overlap or ambiguity between them, as each serves a unique function in the workflow.
All tool names follow a consistent 'discord_verb' pattern (discord_discover, discord_execute, discord_get_schema), using snake_case and clear action verbs. This predictability makes the set easy to understand and navigate.
With only three tools, the server feels thin for a Discord integration, which typically involves many operations like sending messages, managing channels, handling members, etc. The tools act as meta-operations rather than direct actions, which might limit usability and require agents to understand a complex internal schema.
The tool surface is severely incomplete for a Discord server, as it lacks direct operations for core functionalities (e.g., send_message, create_channel, list_members). Instead, it relies on a generic execute tool with external schemas, creating gaps that could lead to agent confusion or failures in common workflows.
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
