Which integrations are available for this server?

Provides tools for sending messages and replying in threads to Slack channels, with automatic channel name resolution.

How do I use Slack Message Sender?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Slack Message Sender Send a message to #general saying 'Hello team!'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Slack Message Sender

by a-g-e-n-t-s

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

MCP_Slack_Server

MCP Server that provides Slack message sending capabilities for Claude Desktop and KADI agents.

Overview

This server is part of the KADI Slack bot architecture. It:

Provides stateless message sending tools
Resolves channel names to IDs automatically
Supports both direct messages and thread replies
Works with Claude Desktop and Agent_TypeScript via KADI broker

Related MCP server: Slack MCP Server

Architecture

Claude Desktop / Agent_TypeScript
              ↓
      KADI Broker (MCP Upstream)
              ↓
    MCP_Slack_Server (this project)
              ↓
      Slack Web API
              ↓
         Slack Channel

Installation

cd C:\p4\Personal\SD\MCP_Slack_Server
npm install

Configuration

Create .env file:

SLACK_BOT_TOKEN=xoxb-your-bot-token
MCP_LOG_LEVEL=info

Required Slack Scopes

chat:write - Send messages to channels
chat:write.public - Send messages to public channels without joining
channels:read - List and resolve channel names
groups:read - Access private channels (if needed)

Usage

Development Mode

npm run dev

Production Mode

npm run build
npm start

As MCP Upstream (via KADI Broker)

Add to kadi-broker/mcp-upstreams.json:

{
  "id": "slack-server",
  "name": "Slack Message Sender",
  "type": "stdio",
  "prefix": "slack",
  "networks": ["global", "slack"],
  "stdio": {
    "command": "node",
    "args": ["C:/p4/Personal/SD/MCP_Slack_Server/dist/index.js"],
    "env": {
      "SLACK_BOT_TOKEN": "xoxb-..."
    }
  }
}

Tools

`send_message`

Send a message to a Slack channel.

Input:

{
  "channel": "#general",  // or "C09T6RU41HP"
  "text": "Hello from Claude!",
  "thread_ts": "1234567890.123456"  // optional
}

Output:

{
  "success": true,
  "message": "Message sent successfully",
  "timestamp": "1234567890.123456",
  "channel": "C09T6RU41HP"
}

`send_reply`

Reply to a message in a thread.

Input:

{
  "channel": "C09T6RU41HP",
  "thread_ts": "1234567890.123456",
  "text": "This is a threaded reply"
}

Output:

{
  "success": true,
  "message": "Reply sent successfully",
  "timestamp": "1234567890.654321",
  "channel": "C09T6RU41HP",
  "thread_ts": "1234567890.123456"
}

Integration Examples

From Claude Desktop

Send a message to #general saying "Hello team!"

From Agent_TypeScript

await client.getBrokerProtocol().invokeTool({
  targetAgent: 'slack-server',
  toolName: 'slack_send_message',
  toolInput: {
    channel: '#general',
    text: 'Hello from Agent_TypeScript!'
  },
  timeout: 10000
});

Reply to Slack Mention

// After getting mention from MCP_Slack_Client
const mention = mentions[0];

await client.getBrokerProtocol().invokeTool({
  targetAgent: 'slack-server',
  toolName: 'slack_send_reply',
  toolInput: {
    channel: mention.channel,
    thread_ts: mention.thread_ts,
    text: claudeResponse
  },
  timeout: 10000
});

License

MIT

Available Tools

2 tools

send_messageB

Send a message to a Slack channel. Can be used by Claude Desktop and KADI agents to send messages to channels or start new threads.

ParametersJSON Schema

Name	Required	Description
`channel`	Yes	Channel ID or name (e.g., #general, C09T6RU41HP)
`text`	Yes	Message text to send
`thread_ts`	No	Optional thread timestamp to reply in an existing thread

TDQS

B3.3/5.0

Behavior2/5

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

No annotations are provided, and the description only states the basic action. It fails to disclose behavioral traits such as authentication requirements, side effects (e.g., message appears immediately), error handling, or whether the operation is destructive.

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?

The description is concise with only two sentences, front-loading the primary purpose and briefly mentioning target users and capability. No unnecessary words.

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?

For a tool with three simple parameters and no output schema, the description covers the basic functionality. However, it lacks information about return values, error conditions, and formatting options like markdown, which would be helpful for an agent.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds no additional semantic information beyond what is in the schema.

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

Purpose4/5

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

The description clearly states the verb 'send' and resource 'message to a Slack channel', specifying it can start new threads. However, it does not explicitly distinguish from sibling 'send_reply' beyond mentioning threads, which is slightly ambiguous.

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

Usage Guidelines3/5

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

The description implies usage for sending new messages or starting threads but provides no explicit guidance on when to use this tool versus the sibling 'send_reply', nor any conditions or exclusions.

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

send_replyA

Reply to a message in a Slack thread. Useful for maintaining conversation context.

ParametersJSON Schema

Name	Required	Description
`channel`	Yes	Channel ID where the thread exists
`thread_ts`	Yes	Thread timestamp to reply to
`text`	Yes	Reply message text

TDQS

A3.7/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only states it replies to a message, but does not disclose failure conditions, permissions, or effects of invalid parameters like thread_ts. Minimal behavioral context.

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?

The description is two sentences, front-loaded with the action, and contains no unnecessary words. Every sentence adds value.

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?

For a simple tool with three parameters and no output schema, the description is adequate but lacks behavioral details such as success/failure indicators or required permissions. Sibling tool provides context.

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

Parameters3/5

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

Schema coverage is 100% with clear parameter descriptions. The tool description does not add any additional semantics beyond what the schema provides, so baseline score of 3 is appropriate.

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 uses a specific verb 'reply' and resource 'message in a Slack thread', clearly distinguishing from the sibling tool 'send_message' which sends new messages.

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?

The phrase 'useful for maintaining conversation context' implies use within a thread, but no explicit when-not-to-use or alternative guidance is provided. However, the distinction from send_message is clear from sibling name.

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.

2 tool updatesv1.0.0Jun 23, 2026
- First observedsend_message
- First observedsend_reply

Deploy Server

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

TDQS

A3.6/5.0

Scored 2026-06-23 18:20 across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one sends a new message or starts a thread, the other replies within a thread. No ambiguity.

Naming Consistency5/5

Both tools follow a consistent 'send_' prefix and verb_noun pattern ('send_message', 'send_reply'), making the naming predictable.

Tool Count3/5

With only 2 tools, the server is very focused. While this is appropriate for a minimal message sender, it feels slightly thin for general Slack interaction.

Completeness3/5

The tool set covers sending and replying, but lacks other common Slack operations (e.g., reading, editing, deleting messages), leaving notable gaps.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Artificial Wit AIOAuth
com.artificialwit
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
ERP Systems CRM Knowledge & Memory
2
QuallaaOAuth
com.quallaa
Talk to your public-facing AI from any MCP client — Claude, ChatGPT, Cursor, Cline, Windsurf.
AI & Machine Learning Communication
2
sendbird A
io.usefulapi
MCP server for Sendbird — chat users, channels, members, and messages from your AI client.
Communication Customer Support
142
Apuchat A
io.github.opcastil11
Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
Communication Agent Orchestration
181

Related MCP Servers

Slack MCP Server
Communication App Automation API Testing
modelcontextprotocol
-
license
Not graded
quality
A
maintenance
MCP Server for the Slack API, enabling Claude to interact with Slack workspaces.
Updated 10 days ago (2026-09-03 01:42 UTC)
70,822
90,196
MIT
Slack MCP Server
Communication Search
coreyepstein
A
license
Not graded
quality
D
maintenance
A Slack MCP server for Claude Code that provides full messaging, channels, search, and threads across multiple Slack workspaces.
Updated 6 months ago (2026-03-04 19:04 UTC)
19
1
MIT
slack-mpm
Communication Workplace & Productivity
bobmatnyc
F
license
B
quality
A
maintenance
MCP server for Slack workspace integration, exposing 40+ Slack operations as tools for Claude Desktop and providing a clean async Python API.
Updated 3 months ago (2026-06-24 02:56 UTC)
64
1
-
Slack MCP Server
Communication Workplace & Productivity
jerrelblankenship
A
license
Not graded
quality
D
maintenance
A Model Context Protocol (MCP) server for Slack integration, allowing Claude to interact with your Slack workspace.
Updated a year ago (2025-10-10 02:04 UTC)
21,854
MIT

MCP_Slack_Server

Overview

Architecture

Installation

Configuration

Required Slack Scopes

Usage

Development Mode

Production Mode

As MCP Upstream (via KADI Broker)

Tools

send_message

send_reply

Integration Examples

From Claude Desktop

From Agent_TypeScript

Reply to Slack Mention

License

Available Tools

TDQS

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Slack MCP Server

Slack MCP Server

slack-mpm

Slack MCP Server

`send_message`

`send_reply`