Skip to main content
Glama
pilat

mcp-notify

by pilat
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

mcp-notify

Minimal MCP server for sending Slack messages. Supports both bot tokens (xoxb) and user tokens (xoxc + cookie auth). Fire-and-forget — single send_message tool, nothing else.

Looking for a full-featured Slack MCP? Check out korotovsky/slack-mcp-server — it supports reading, searching, reactions, threads, DMs, and much more. We recommend it for most use cases.

This project exists because we needed two things it doesn't offer:

  • Bot signature — in user-token mode, every message gets a :robot_face: context block so it's clear the message was sent by an AI assistant, not a human. In bot-token mode, the app name/icon already serves this purpose.

  • Concurrent safety — SQLite with WAL mode and check-lock-recheck sync pattern, safe for multiple MCP instances running in parallel

Installation

Claude Code

Add to your MCP config (~/.claude.json globally or .mcp.json per project).

Bot token (recommended for Slack apps):

{
  "mcpServers": {
    "mcp-notify": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@pilat/mcp-notify"],
      "env": {
        "SLACK_MCP_BOT_TOKEN": "xoxb-..."
      }
    }
  }
}

User token (xoxc + cookie):

{
  "mcpServers": {
    "mcp-notify": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@pilat/mcp-notify"],
      "env": {
        "SLACK_MCP_XOXC_TOKEN": "xoxc-...",
        "SLACK_MCP_XOXD_TOKEN": "xoxd-..."
      }
    }
  }
}

Other MCP clients

Use npx @pilat/mcp-notify as the command with stdio transport. Pass credentials as environment variables:

# Bot token
SLACK_MCP_BOT_TOKEN=xoxb-... npx @pilat/mcp-notify

# User token
SLACK_MCP_XOXC_TOKEN=xoxc-... SLACK_MCP_XOXD_TOKEN=xoxd-... npx @pilat/mcp-notify

Related MCP server: Slack MCP Server

Environment Variables

Variable

Required

Description

SLACK_MCP_BOT_TOKEN

One of bot/user

Bot token (xoxb-...) from your Slack app

SLACK_MCP_XOXC_TOKEN

One of bot/user

User's xoxc-... token

SLACK_MCP_XOXD_TOKEN

With xoxc

User's xoxd-... session token (value of the d cookie)

SLACK_MCP_DATA_DIR

No

Custom path for SQLite cache (default: ~/.local/share/mcp-notify)

Set either SLACK_MCP_BOT_TOKEN or SLACK_MCP_XOXC_TOKEN + SLACK_MCP_XOXD_TOKEN. Setting both bot and user tokens is an error.

Bot token setup

  1. Create a Slack app at api.slack.com/apps

  2. Add the following OAuth scopes: channels:read, groups:read, users:read, usergroups:read, chat:write

  3. Install the app to your workspace

  4. Copy the Bot User OAuth Token (xoxb-...)

User token setup (xoxc + cookie)

  1. Open Slack in browser (not desktop app)

  2. Open DevTools → Network tab

  3. Make any action in Slack (switch channel, send message)

  4. Find any request to api.slack.com → Headers tab

  5. SLACK_MCP_XOXC_TOKEN: from request payload, find token=xoxc-...

  6. SLACK_MCP_XOXD_TOKEN: from Cookie header, find d=xoxd-... — copy only the xoxd-... part (without d=)

Architecture

Single tool: send_message. In user-token mode, messages include a :robot_face: context block. In bot-token mode, messages are sent without the signature (the app name/icon already identifies the sender). Both modes use Block Kit with plain text fallback.

  • SQLite cache (~/.local/share/mcp-notify/data.db, WAL mode) — channels, users, user groups with lazy sync on first cache miss, 24h TTL

  • Mention resolution — @username → <@U123>, @grouphandle → <!subteam^ID>. Groups take priority. Resolved in parallel.

  • Concurrent sync safety — CAS-based check-lock-recheck pattern via sync_meta table

Available Tools

1 tool
send_messageA

Send a message to a Slack channel or thread. In user-token mode, messages are tagged with :robot_face: so recipients know it was AI-assisted. In bot-token mode, the app identity serves this purpose.

NOTE: This tool posts to channels only. DMs are not supported.

MENTIONS: Write @username or @groupname naturally — they are auto-resolved. Do NOT construct <@U...> syntax manually.

SLACK URLs: When given a Slack URL like .../archives/C0AGCGG628K/p1718033467085279:

  • Channel ID: the segment after /archives/ → pass as channel

  • Thread timestamp: strip "p", insert dot before last 6 digits → "1718033467.085279" Prefer channel ID over channel name when both are available.

FORMAT — Slack mrkdwn (NOT Markdown): bold italic strike code block <https://url|link text> > quote • bullets :emoji_name: NEVER use: bold, text, # headers, --- rules, tables, ![images].

ParametersJSON Schema
NameRequiredDescriptionDefault
channelYesChannel name (without #) or channel ID. Examples: "general", "C0AGCGG628K". Prefer ID when available; never guess a name you weren't given.
messageYesMessage text in Slack mrkdwn format. @mentions are auto-resolved.
thread_tsNoThread timestamp for replying in a thread (e.g. "1718033467.085279"). See URL extraction in tool description.
reply_broadcastNoWhen replying in a thread (thread_ts required), also post the message to the channel. Like the "Also send to #channel" checkbox in Slack.

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description fully discloses behaviors: messages are tagged with :robot_face: in user-token mode, mentions are auto-resolved, and formatting uses Slack mrkdwn. It does not cover potential side effects or rate limits, but the core behavioral traits are well explained.

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

Conciseness4/5

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

The description is relatively long but well-structured with clear sections (NOTE, MENTIONS, SLACK URLs, FORMAT). It front-loads the core purpose and then provides necessary details. Every sentence adds value, though some agents might find it slightly verbose.

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

Completeness3/5

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

Given the tool's complexity (4 parameters, 100% schema coverage), the input side is well-covered. However, there is no output schema, and the description does not explain the return value (e.g., message timestamp, error handling). For a complete understanding, the agent might need to infer this from context.

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

Parameters5/5

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

The schema has 100% parameter description coverage, yet the tool description adds significant extra meaning: e.g., 'channel' advises preferring ID and avoiding name guessing, 'thread_ts' details URL extraction, and 'reply_broadcast' explains the checkbox analogy. This greatly aids the agent in correct parameter usage.

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 message to a Slack channel or thread, distinguishing between user-token and bot-token modes. It specifies that it only posts to channels, not DMs, making the purpose unambiguous and distinct from any potential sibling tools.

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

Usage Guidelines5/5

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

The description provides explicit guidelines: when to use (sending messages to channels), what not to use (DMs not supported), and how to handle mentions and Slack URL extraction. It also includes formatting instructions, giving the agent clear rules for correct invocation.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.6/5.0
Disambiguation5/5

Only one tool exists, so there is no risk of confusion between tools. The tool's purpose is clearly described.

Naming Consistency5/5

With a single tool, naming consistency is perfect. 'send_message' follows a clear verb_noun pattern.

Tool Count4/5

One tool is minimal, but it is appropriate for a simple notification server. While it could be expanded with additional utilities, the scope is well-defined and not excessive.

Completeness5/5

The tool covers all necessary aspects for sending Slack notifications: channel targeting, threading, formatting, mentions, and URL parsing. No obvious gaps for its intended purpose.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Slack Notify MCP

    SilasReinagel
    A
    license
    Not graded
    quality
    D
    maintenance
    MCP server for posting messages to Slack channels via webhooks or bot API. Supports configurable usernames, emojis, and both webhook and bot token authentication modes.
    17
    MIT

  • slack-mcp

    EgumaYuto
    A
    license
    Not graded
    quality
    B
    maintenance
    MCP server for interacting with Slack using a user token. It allows reading channels, DMs, threads, search, and posting messages as the authenticated user.
    54
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pilat/mcp-notify'

If you have feedback or need assistance with the MCP directory API, please join our Discord server