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/hypark5540/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/hypark5540/discord-mcp/gemini-extension)<a href="https://agentmods.dev/plugins/hypark5540/discord-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/hypark5540/discord-mcp/gemini-extension/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/hypark5540/discord-mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/hypark5540/discord-mcp/gemini-extension.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 1mo ago.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "discord-mcp",
"version": "0.1.1",
"description": "Safe, configurable Discord access through the Model Context Protocol",
"mcpServers": {
"discord": {
"command": "npx",
"args": ["-y", "@hypark5540/[email protected]"],
"env": {
"DISCORD_TOKEN": "${DISCORD_TOKEN}",
"DISCORD_ALLOWED_GUILD_IDS": "${DISCORD_ALLOWED_GUILD_IDS:-}",
"DISCORD_ALLOWED_CHANNEL_IDS": "${DISCORD_ALLOWED_CHANNEL_IDS:-}",
"DISCORD_ENABLE_WRITES": "${DISCORD_ENABLE_WRITES:-false}",
"DISCORD_ENABLE_DELETES": "${DISCORD_ENABLE_DELETES:-false}",
"DISCORD_ALLOW_UNRESTRICTED_WRITES": "${DISCORD_ALLOW_UNRESTRICTED_WRITES:-false}",
"DISCORD_MAX_RESPONSE_CHARS": "${DISCORD_MAX_RESPONSE_CHARS:-50000}"
}
}
},
"settings": [
{
"name": "Discord Bot Token",
"description": "Bot token from the Discord Developer Portal. Never use a user token.",
"envVar": "DISCORD_TOKEN",
"sensitive": true
},
{
"name": "Allowed Discord server IDs",
"description": "Optional comma-separated guild IDs. Leave blank to use every guild visible to the bot.",
"envVar": "DISCORD_ALLOWED_GUILD_IDS"
},
{
"name": "Allowed Discord channel IDs",
"description": "Optional comma-separated channel IDs. Leave blank to use every channel in an allowed guild.",
"envVar": "DISCORD_ALLOWED_CHANNEL_IDS"
},
{
"name": "Enable message writes",
"description": "Set true to expose send and own-message edit tools. The default is false.",
"envVar": "DISCORD_ENABLE_WRITES"
},
{
"name": "Enable message deletes",
"description": "Set true to expose confirmed own-message deletes. Writes must also be enabled.",
"envVar": "DISCORD_ENABLE_DELETES"
},
{
"name": "Allow writes without an allowlist",
"description": "Set true only to deliberately permit writes in every visible guild channel.",
"envVar": "DISCORD_AWhat ships with it
8 files beside gemini-extension.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.
- scripts/build-mcpb.mjs 4.5 KB runs code
- scripts/build-npm-bootstrap.mjs 3.3 KB runs code
- scripts/bundle-python.mjs 8.6 KB runs code
- scripts/check-versions.mjs 10 KB runs code
- scripts/smoke-stdio.mjs 3.4 KB runs code
- scripts/verify-mcpb.mjs 4.6 KB runs code
- scripts/verify-published-artifacts.mjs 2.9 KB runs code
- scripts/verify-sbom.mjs 4.5 KB runs code
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.
- 1mo ago First seen · 59 lines scan A 4907d4b0fb1b
discord-mcp is a plugin published in the GitHub repository hypark5540/discord-mcp (0 stars, last pushed yesterday), 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 2026-09-07.
Other plugins, from other repositories
claude-settings marketplace
Plugin marketplace listing 38 plugins: simplify, humanize, fable-advisor, codex-advisor, adhd-output-style.
gcloud-tools
Query Google Cloud logs, metrics, and traces through the Cloud Observability MCP.
business
Business — 11 free skills bundled together.
academic
Academic — 2 free skills bundled together.
porkbun
Manage the domains you own at Porkbun from Claude: DNS, nameservers, forwarding, DNSSEC, restore points and Secure Static Hosting, including publishing a site Claude builds for you.
whimsical
Whimsical's official MCP server. Create and edit boards, docs, flowcharts, mind maps, sequence diagrams, wireframes, tables and sticky notes, then read, search and comment on anything already in the workspace. OAuth 2.1, no API key; a free Whimsical account can use every tool.