Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/PaSympa/discord-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/pasympa/discord-mcp/plugin)<a href="https://agentmods.dev/plugins/pasympa/discord-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/pasympa/discord-mcp/plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/pasympa/discord-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/pasympa/discord-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
discord-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "discord-mcp",
"version": "2.4.0",
"description": "Run your Discord from Claude Code through your own bot: messages, moderation, roles, channels, forums, webhooks and events, plus a channel digest and a moderation sweep skill.",
"author": {
"name": "PaSympa",
"url": "https://github.com/PaSympa"
},
"homepage": "https://github.com/PaSympa/discord-mcp#readme",
"repository": "https://github.com/PaSympa/discord-mcp",
"license": "MIT",
"keywords": ["discord", "discord-bot", "discord-api", "moderation", "bot", "mcp"],
"userConfig": {
"discord_token": {
"type": "string",
"title": "Discord bot token",
"description": "Bot token from the Bot page of the Discord Developer Portal.",
"sensitive": true,
"required": true
},
"toolsets": {
"type": "string",
"title": "Toolsets",
"description": "Comma-separated toolsets to expose, such as discovery,messages. Empty exposes every tool. An unknown name stops the server at startup.",
"default": ""
},
"read_only": {
"type": "boolean",
"title": "Read-only mode",
"description": "Expose only the tools annotated readOnlyHint: true. Write tools are neither listed nor callable.",
"default": false
},
"allowed_guilds": {
"type": "string",
"title": "Allowed guilds",
"description": "Comma-separated guild IDs the server may act on. Calls that target any other guild are rejected. Empty allows every guild.",
"default": ""
},
"message_content": {
"type": "boolean",
"title": "Message Content intent",
"description": "Request the Message Content privileged intent at connect time. Turn it off if the intent is disabled in the Developer Portal.",
"default": true
},
"guild_members": {
"type": "boolean",
"title": "Server Members intent",
"description": "Request the Server Members privileged intent at connect time. Turn it off if the intent What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 172 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 67 lines scan A c7f7d445bee2
discord-mcp is a plugin published in the GitHub repository PaSympa/discord-mcp (34 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-16.
discord-mcp compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| discord-mcpPaSympa/discord-mcp | Plugin | 34 | today | MIT | A | — | Claude Code |
| obsidian-mcp-servercyanheads/obsidian-mcp-server | Plugin | 706 | 5d ago | Apache-2.0 | A | — | Claude Code |
| ntfy-mcp-servercyanheads/ntfy-mcp-server | Plugin | 25 | 2d ago | Apache-2.0 | A | — | Claude Code |
| murmuralexfrmn/murmur | Plugin | 21 | 26d ago | MIT | A | — | Claude Code |
| plonkostapondo/Plonk | Plugin | 17 | 27d ago | MIT | A | — | Claude Code |
| todoxbeydemirfurkan/todox | Plugin | 2 | 6d ago | MIT | A | — | Claude Code |
| slack-mcpadelaidasofia/slack-mcp | Plugin | 2 | 7d ago | MIT | A | — | Claude Code |