Skip to main content
Glama
0xShaito

discord-dm-mcp

by 0xShaito

discord-dm-mcp

A tiny MCP server that lets Claude send Discord direct messages through a bot — with nothing to host.

Sending a DM is just two stateless HTTPS POSTs to Discord's REST API, so there is no gateway/websocket connection to keep alive and no server to run. This package is a stdio MCP server: it runs as a subprocess of whatever launches it — your local Claude client, or a Claude cloud routine via a committed .mcp.json. Each user brings their own Discord bot token; the package itself holds no secrets.

It exposes a single tool, send_discord_dm.


How "no hosting" works

Where you use it

Where the server runs

You host a machine?

Local Claude Code / Desktop / Cursor

your laptop (a subprocess)

No

Claude cloud routine (via .mcp.json)

Anthropic's ephemeral sandbox

No

The only path that would require hosting is a remote ("Connector chip") MCP server, because a remote MCP must be reachable at a URL. This package avoids that by using stdio. (See the trade-off.)


Related MCP server: Discord Bridge MCP Server

Prerequisites (one-time Discord setup)

  1. Create a bot. https://discord.com/developers/applications → New Application → BotReset Token → copy the token. This is your DISCORD_BOT_TOKEN.

    • You do not need any privileged intents (Message Content, etc.) — those gate the gateway, not REST sends. This bot never reads messages.

  2. Invite the bot to your server with the bot scope and zero permissions (DMs aren't governed by a permission bit):

    https://discord.com/oauth2/authorize?client_id=YOUR_APP_ID&scope=bot&permissions=0
  3. The bot must share that server with every recipient. Discord only delivers a DM if the bot and the user have a mutual guild. Otherwise the send fails with error 50007 ("Cannot send messages to this user"). The recipient must also not have DMs disabled / the bot blocked.

  4. Get recipient user IDs. In Discord: Settings → Advanced → Developer Mode on, then right-click a user → Copy User ID. (Or build a consented GitHub→Discord mapping.)


Install — local Claude clients

No repo, no GitHub needed — just npm:

claude mcp add discord-dm \
  --env DISCORD_BOT_TOKEN="your-bot-token" \
  -- npx -y discord-dm-mcp

For Claude Desktop / Cursor, add the equivalent to the client's MCP config:

{
  "mcpServers": {
    "discord-dm": {
      "command": "npx",
      "args": ["-y", "discord-dm-mcp"],
      "env": { "DISCORD_BOT_TOKEN": "your-bot-token" }
    }
  }
}

Install — Claude cloud routine

A cloud routine can't use a local stdio server you added with claude mcp add (that lives on your machine). Instead the routine clones a repo and reads .mcp.json from it. So:

  1. Point the routine at a repo that contains a .mcp.json (the one at the root of this repo works as-is — it npx-installs the published package):

    {
      "mcpServers": {
        "discord-dm": {
          "command": "npx",
          "args": ["-y", "discord-dm-mcp"],
          "env": { "DISCORD_BOT_TOKEN": "${DISCORD_BOT_TOKEN}" }
        }
      }
    }

    The repo can be a near-empty stub — its only job is to carry this file. The ${DISCORD_BOT_TOKEN} is expanded from the routine's environment variable.

  2. Set the env var. In the routine's environment ("Default" or a custom one) add an Environment variable DISCORD_BOT_TOKEN=....

    ⚠️ Claude routines have no dedicated secrets store yet — env vars are visible to anyone who can edit the environment and may appear in transcripts. Treat this token as low-confidentiality and scope the bot to least privilege (it needs no guild permissions). Rotate it if a transcript is shared.

  3. Allow Discord egress. The Default environment's "Trusted" network access blocks discord.com (requests fail with 403 host_not_allowed). Edit the environment's Network access to Full, or Custom with discord.com added to the allowlist. (Custom-allowlist propagation has had bugs; if Discord still 403s, use Full.)

  4. Reference the tool from the routine Instructions, e.g. "If you're unsure whether to merge, call send_discord_dm to ask the PR author."

Running from a checkout instead of npm (e.g. before publishing): copy examples/.mcp.local-repo.json to the repo root as .mcp.json and set the environment Setup script to npm ci && npm run build.


Tool: send_discord_dm

Field

Type

Notes

discordUserId

string

Recipient's numeric Discord ID. One of this or githubLogin is required.

githubLogin

string

Resolved to a Discord ID via DISCORD_USER_MAP.

content

string

Plain message text, sent as-is.

escalation

object

Structured decision request (formatted into the body). Fields below.

escalation.prUrl

string

Link to the PR / item.

escalation.uncertainty

string

What the agent is unsure about.

escalation.evidence

string

Relevant evidence / context.

escalation.options

string[]

Rendered as A) … B) … plus a Custom) option.

escalation.recommendation

string

The agent's recommended option.

dryRun

boolean

Resolve + format but never call Discord.

Provide content, escalation, or both. Mentions are always disabled (allowed_mentions: { parse: [] }), so messages never accidentally ping @everyone, roles, or users.

Errors are returned as tool errors (isError: true), not thrown: unknown recipient, missing token, the no-mutual-guild 50007/50278 case (not retried), and other Discord API failures. Rate-limit 429s are retried automatically honoring Retry-After.


Configuration (environment variables)

Var

Required

Purpose

DISCORD_BOT_TOKEN

to send

Bot token. Not needed for dry runs.

DISCORD_DRY_RUN

no

1/true/yes forces dry-run globally.

DISCORD_USER_MAP

no

Inline JSON or path to a {githubLogin: discordUserId} file.

DISCORD_API_BASE

no

Override https://discord.com/api/v10.

Mapping GitHub logins to Discord IDs

Set DISCORD_USER_MAP to inline JSON ({"octocat":"123..."}) or a file path (see examples/mapping.example.json). Keys match the GitHub login case-insensitively. For a consented mapping, have users link their own GitHub via Discord OAuth2 (identify + connections scopes) and only DM logins present in the map.


Develop / verify

npm install
npm run build      # tsc -> dist/
npm test           # unit tests (pure functions)
npm run smoke      # builds, starts the server over stdio, calls the tool in dry-run

npm run smoke proves the full MCP round-trip with no token and no network.


Why stdio and not a remote connector?

A custom connector (the chip in Claude's "Connectors" UI) is a remote MCP server: Claude connects out to a URL, so it must be hosted (even serverless = a deployment). A stdio server runs as a child process of the client, so it needs no host. The trade:

  • stdio (this package): no hosting; works locally and in cloud routines via .mcp.json. Not shown as a Connector chip.

  • remote connector: shown as a chip and reusable across clients, but you must host (serverless like Cloudflare Workers is the lightest option).


Responsible use

Discord's Developer Policy requires consent before initiating processes on a user's behalf and prohibits unsolicited / bulk DMs. Use this for opted-in, transactional, one-at-a-time notifications (e.g. asking a PR author a question), never to broadcast. Using a user token / selfbot to DM is forbidden by Discord and can get the account terminated — this package uses a proper bot token only.

License

MIT

Available Tools

1 tool
send_discord_dmSend Discord DMA

Send a direct message to a Discord user via a bot (REST only, no gateway). Provide either discordUserId or githubLogin (resolved via the configured mapping). Supply content for a plain message, and/or escalation to format a decision request. Mentions are always disabled (allowed_mentions.parse=[]). The bot must share a server with the recipient or Discord returns error 50007. Only DM users who have opted in — never mass-DM.

ParametersJSON Schema
NameRequiredDescriptionDefault
dryRunNoIf true, resolve + format but do NOT call Discord
contentNoPlain message text to send as-is
escalationNoStructured decision request; formatted into the message body
githubLoginNoGitHub login; resolved to a Discord user ID via DISCORD_USER_MAP
discordUserIdNoDiscord numeric user ID (snowflake) of the recipient

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses key behaviors: mentions always disabled, server sharing requirement, opt-in policy, and dryRun flag. No annotations exist, so description carries full burden. Does not cover rate limits or authentication, but sufficient for safe usage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five sentences efficiently cover purpose, parameters, constraints, and policy. Front-loaded with core purpose, no redundancy. Every sentence is informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all critical aspects: identification, message types, constraints, and opt-in policy. Missing description of return value or error handling beyond error 50007, but sufficient for a direct message tool with no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description adds value by explaining usage patterns (e.g., 'Supply content for a plain message, and/or escalation'), resolving githubLogin via mapping, and detailing dryRun behavior. Escalation object purpose is clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool sends a direct message to a Discord user via a bot, specifying REST-only and no gateway. It distinguishes between plain messages and structured escalation requests, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: when to DM (for opted-in users), how to identify recipients (discordUserId or githubLogin), and prerequisites (bot must share server). Lacks explicit 'when not to use' but given no siblings, this is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.0
    • First observedsend_discord_dm

TDQS

A4.2/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no ambiguity. An agent cannot confuse it with another tool.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (send_discord_dm), consistent with common MCP conventions.

Tool Count3/5

A single tool for sending DMs is minimal but arguably appropriate if the server's sole purpose is to send DMs. However, it feels thin and could benefit from at least one more tool (e.g., to verify user availability).

Completeness2/5

The server only supports sending messages, lacking any way to check user opt-in status, retrieve conversation history, or handle errors like 50007. This leaves significant gaps for an agent.

Maintenance

ActivityInactive
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers