DiscordSAFE
MCP server for full Discord server administration via Claude - 128 operations for messages, moderation, channels, roles, events, and more
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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.
Features
- 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...
Prerequisites
- Python 3.12+
- uv package manager
- A Discord account
- A Discord server where you have admin permissions
Installation
Option A: Editable Install (Recommended)
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.
Option B: Run from Directory
Clone and run directly without installing:
git clone https://github.com/glittercowboy/discord-mcp.git cd discord-mcp uv sync
Discord Bot Setup
Follow these steps carefully to create and configure your Discord bot.
Step 1: Create a Discord Application
- Go to the Discord Developer Portal
- Log in with your Discord account
- Click the "New Application" button (top right)
- Enter a name for yo
78d52ba00023OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add discord-mcp --env DISCORD_BOT_TOKEN=${DISCORD_BOT_TOKEN} -- uvx discord-mcp{
"mcpServers": {
"discord-mcp": {
"command": "uvx",
"args": [
"discord-mcp"
],
"env": {
"DISCORD_BOT_TOKEN": "${DISCORD_BOT_TOKEN}"
}
}
}
}Exposed tools (3)
2 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
discord_discover | read | Browse all available Discord operations organized by category. |
discord_execute | write | Execute a Discord operation with specified parameters. |
discord_get_schema | read | Get detailed parameter schema for a specific operation. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
78d52ba00023full audit observations/trust-audit/mcp-server/glittercowboy__discord-11.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 78d52ba00023 | SAFE | B | 89 | first audit |
Questions
What is the Discord MCP server?
MCP server for full Discord server administration via Claude - 128 operations for messages, moderation, channels, roles, events, and more
What tools does Discord expose?
3 in total: 2 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Discord safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Discord need?
It reads DISCORD_BOT_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (78d52ba00023), read on 2026-10-08. The repository is watched and re-audited when it changes.