Which integrations are available for this server?

Provides tools for fetching and processing Slack messages, including retrieving recent messages from channels, getting messages from specific users, summarizing channel conversations, and grouping messages by sender

How do I use mcp_slack?

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., "@mcp_slack summarize the last 50 messages in the general channel" 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.

mcp_slack

by Abu-BakarYasir

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

Slack-MCP

This project is a Multi-Tool MCP (Model Context Protocol) server for Slack automation using the FastMCP library. It allows you to fetch and process Slack messages using AI agents.This project is great example to learn and Build Understanding reagarding MCPs.

📂 Folder Structure

slack-mcp/
├── main.py               # Main MCP tool server with multiple tools
├── .env                  # Store your SLACK_TOKEN safely here
├── smithery.yaml         # Configuration for Smithery deployment
├── README.md             # This file
├── uv-lock
└── pyproject.toml        # Python dependencies

Related MCP server: Agent Communication MCP Server

🚀 Tools in This MCP

1. `get_recent_messages`

Fetches the most recent messages from a given Slack channel.

Inputs: channel_id, limit
Returns: Formatted recent messages.

2. `get_user_messages`

Fetches messages from a specific user within a channel.

Inputs: channel_id, username, limit
Returns: Messages sent by the user.

3. `summarize_recent_messages`

Summarizes the last N messages from a channel using a connected LLM.

Inputs: channel_id, limit
Returns: AI-generated summary.

4. `group_messages_by_user`

Groups recent channel messages by sender.

Inputs: channel_id, limit

Returns: A grouped format like:

@user1:
- Message 1
- Message 2

@user2:
- Message A

🚪 Slack OAuth Setup & Token Generation

1. Create a Slack App

Go to: https://api.slack.com/apps
Click Create New App > From Scratch
Give it a name and choose your workspace

2. Set OAuth Scopes

In OAuth & Permissions, under Bot Token Scopes, add:

channels:read
channels:history
users:read
chat:write (optional for sending messages)

3. Install to Workspace

Click Install App to Workspace
Authorize permissions
Copy the Bot User OAuth Token (starts with xoxb-...)

4. Save the Token

Create a .env file:

SLACK_TOKEN=xoxb-your-token-here

If you change scopes later:

Revisit OAuth & Permissions
Click Reinstall App to apply new scopes

✨ Testing the Tools

On MCP Inspector (Local)

Run the server:

python main.py

Use MCP Inspector to call tools and test output

mcp dev main.py

On Smithery (Cloud)

Push your code to GitHub
Deploy your MCP to Smithery
Use the "Run tool" tab to test individual tools

On Claude (Cloud Desktop)

You can connect these tools via Smithery to Claude workflows for real-time Slack insights and summaries.

🚜 Requirements

Install dependencies with:

uv pip install -r pyproject.toml

Or manually:

pip install fastmcp httpx python-dotenv

🔧 Environment File (.env)

SLACK_TOKEN=xoxb-123-your-token

🎉 Contributing

Pull requests are welcome. If you’d like to add new Slack tools (e.g., send_message, track_reactions, etc.), feel free to open an issue or PR.

📹 Video Demo On claude desktop:

https://github.com/user-attachments/assets/37d905a5-6382-40ce-9500-2dd744656546

🙏 Acknowledgments

FastMCP by Model Context Protocol
Smithery.ai for deploying and testing MCPs
Slack Web API Docs: https://api.slack.com/

📊 Example Output

Grouped Slack Messages:

@bakar:
- Just pushed latest PR
- Working on the backend API

@hamza:
- Updated Figma designs
- Fixed navbar bug

📊 Smithery.ai (Cloud Deployment)

Here is the URL go and checkout this mcp_server: Slack_MCP_Server

🧑‍💻 Author

Built by Abu Bakar Yasir — Computer Engineering @ COMSATS + AI Software Engineer | Full Stack Developer 🚀

Available Tools

4 tools

get_recent_slack_messagesC

Fetch recent messages from a Slack channel.

ParametersJSON Schema

Name	Required	Description	Default
`channel_id`	Yes
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'fetch' but doesn't specify whether this is a read-only operation, requires authentication, has rate limits, or how it handles errors. This leaves significant gaps in understanding the tool's behavior.

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 a single, clear sentence with no wasted words, making it highly concise and front-loaded. It efficiently communicates the core purpose without unnecessary elaboration.

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 low complexity (2 parameters, no annotations, but with an output schema), the description is minimally adequate. The output schema likely covers return values, reducing the need for description details, but the description fails to address key behavioral aspects like permissions or error handling, leaving it incomplete for safe use.

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

Parameters2/5

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

Schema description coverage is 0%, so the schema provides no parameter details. The description adds minimal semantics by implying 'channel_id' and 'limit' are used to fetch messages, but it doesn't explain what 'recent' means, the format of 'channel_id', or default behavior for 'limit' (though the schema shows a default of 5). This insufficiently compensates for the lack of schema documentation.

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 action ('fetch') and resource ('recent messages from a Slack channel'), making the purpose understandable. However, it doesn't differentiate from sibling tools like 'get_user_messages' which might also retrieve messages, leaving room for ambiguity.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives such as 'get_user_messages' or 'post_message'. The description lacks context about prerequisites, constraints, or typical use cases, offering minimal direction.

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

get_user_infoB

Get Slack user info by username or real name.

Args:
    username: Slack display name or real name (not user ID).

ParametersJSON Schema

Name	Required	Description	Default
`username`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.3/5.0

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 of behavioral disclosure. It mentions that the tool retrieves user info but doesn't specify what info is returned (e.g., profile details, status), whether it requires authentication, rate limits, or error handling. This leaves significant gaps in understanding the tool's behavior beyond basic functionality.

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 appropriately sized and front-loaded, with the main purpose stated clearly in the first sentence. The additional parameter explanation is concise and adds value without redundancy. However, the formatting with quotes and line breaks slightly detracts from optimal structure.

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 that there's an output schema (which should cover return values), the description doesn't need to explain outputs. However, for a tool with no annotations and only basic parameter info, it lacks details on behavioral aspects like authentication or error cases. It's adequate but has clear gaps in providing a complete context for effective use.

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?

The description adds meaningful context for the single parameter: 'username: Slack display name or real name (not user ID).' This clarifies the parameter's purpose and constraints beyond the schema, which has 0% description coverage. Since there's only one parameter and the description compensates well, it earns a high score.

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 tool's purpose: 'Get Slack user info by username or real name.' It specifies the verb ('Get'), resource ('Slack user info'), and scope ('by username or real name'), making it easy to understand what the tool does. However, it doesn't explicitly distinguish this tool from its sibling tools (e.g., get_user_messages), which slightly limits its differentiation.

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 by specifying 'by username or real name' and noting that it's 'not user ID,' which helps clarify when to use this tool versus alternatives that might use IDs. However, it doesn't explicitly state when to use this tool over siblings like get_user_messages or provide clear exclusions, leaving some ambiguity.

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

get_user_messagesB

Fetch messages by a specific user (given by name) from a Slack channel.

Args:
    channel_id: The Slack channel ID.
    username: The Slack username or real name of the user.
    limit: How many messages to check (optional).

ParametersJSON Schema

Name	Required	Description	Default
`channel_id`	Yes
`username`	Yes
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

B3.4/5.0

Behavior2/5

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

With no annotations, the description carries full burden but only states basic functionality. It doesn't disclose behavioral traits like permissions needed, rate limits, pagination, error handling, or whether it's read-only (implied by 'Fetch' but not explicit). This is inadequate for a tool with potential Slack API constraints.

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 front-loaded with the core purpose, followed by a concise Args section. Every sentence adds value: the first defines the tool, and the param explanations are necessary. No redundant or verbose content.

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 3 parameters, no annotations, and an output schema (which handles return values), the description is minimally adequate. It covers purpose and param semantics but lacks behavioral context (e.g., Slack API nuances). For a tool interacting with external services, more completeness is needed.

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?

The description adds meaningful context beyond the schema: it explains 'username' includes 'real name' (not just username), 'limit' checks messages (not fetches exactly that many), and clarifies the purpose of each param. With 0% schema description coverage, this compensates well, though 'channel_id' semantics could be more detailed.

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 action ('Fetch messages') and target ('by a specific user from a Slack channel'), specifying the resource (messages) and scope (user, channel). It distinguishes from siblings like 'get_recent_slack_messages' (general messages) and 'post_message' (sending), but not explicitly from 'get_user_info' (user metadata).

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 when needing messages from a specific user in a channel, but lacks explicit guidance on when to use this vs. 'get_recent_slack_messages' (e.g., for filtering) or 'get_user_info' (for user details). No exclusions or prerequisites are mentioned.

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

post_messageC

Post a message to a Slack channel.

ParametersJSON Schema

Name	Required	Description	Default
`channel_id`	Yes
`text`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states the action ('Post') but doesn't mention any behavioral traits like required permissions, rate limits, whether the message is editable, or what happens on success/failure. This leaves significant gaps for a mutation tool.

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 a single, efficient sentence that directly states the tool's function without any wasted words. It's appropriately sized and front-loaded with the core purpose.

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 this is a mutation tool with no annotations, 0% schema coverage, but an output schema exists, the description is minimally adequate. The output schema may cover return values, but the description lacks context about permissions, error handling, or usage scenarios, leaving it incomplete for safe operation.

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

Parameters2/5

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

Schema description coverage is 0%, so the description must compensate but adds no parameter information. It doesn't explain what 'channel_id' represents (e.g., format like C123456) or what 'text' can contain (e.g., markdown, emojis, attachments). This leaves both parameters semantically unclear.

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 action ('Post a message') and target resource ('to a Slack channel'), making the purpose immediately understandable. However, it doesn't differentiate this from sibling tools like 'get_recent_slack_messages' or 'get_user_messages', which prevents a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. There are sibling tools for retrieving messages, but no indication of when posting is appropriate versus reading, or any prerequisites like channel access permissions.

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.

4 tool updatesv1.0.0Jan 3, 2026
- Changedget_recent_slack_messages1 field changed
  - addedInput schema / title
```
Added value: +"get_recent_slack_messagesArguments"
```
- Changedget_user_info1 field changed
  - addedInput schema / title
```
Added value: +"get_user_infoArguments"
```
- Changedget_user_messages1 field changed
  - addedInput schema / title
```
Added value: +"get_user_messagesArguments"
```
- Changedpost_message1 field changed
  - addedInput schema / title
```
Added value: +"post_messageArguments"
```
4 tool updatesNov 17, 2025
- First observedget_recent_slack_messages
- First observedget_user_info
- First observedget_user_messages
- First observedpost_message

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.2/5.0

Scored 2026-04-18 09:06 across 4 tools

Disambiguation4/5

The tools are mostly distinct, but get_recent_slack_messages and get_user_messages could be confused as both fetch messages from channels. However, get_user_messages specifies a user filter, which helps differentiate it. The other tools (get_user_info, post_message) have clear, non-overlapping purposes.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (e.g., get_recent_slack_messages, post_message). There are no deviations in naming conventions, making the set predictable and readable.

Tool Count3/5

With only 4 tools, the server feels thin for a Slack integration, which typically involves more operations like managing channels, files, or reactions. However, it covers basic messaging and user info, so it's borderline but not severely lacking.

Completeness3/5

The server covers core messaging operations (post and fetch) and user info, but there are notable gaps such as updating or deleting messages, listing channels, or handling reactions. Agents can work around this for basic tasks, but advanced workflows may fail.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

stream A
io.usefulapi
Query channels, search messages, and read threads, users and reactions in your Stream Chat app.
Communication Search
132
ParleyOAuth
io.idntty
Message channels between the agents of different people, one-to-one or in groups.
Communication Agent Orchestration
1
Bot Rooms — Agent Conversations A
io.github.flath12
Agent-to-agent chat: find rooms, read messages, post and reply.
Communication Autonomous Agents
141
WaAPIOAuth
app.waapi
Messaging tools for AI agents: send messages, manage chats, groups and channels.
Communication Workplace & Productivity
1

Related MCP Servers

mcp-server-chatsum
Text Summarization Communication
chatmcp
F
license
Not graded
quality
D
maintenance
Summarizes your chat messages.
Updated 2 years ago (2024-12-04 02:58 UTC)
1,027
-
Agent Communication MCP Server
Communication Agent Orchestration Autonomous Agents
mkXultra
A
license
Not graded
quality
A
maintenance
Enables AI agents to communicate with each other through Slack-like room-based channels with messaging, mentions, presence management, and long-polling for real-time collaboration.
Updated 2 days ago (2026-09-19 06:01 UTC)
1,014 npm
4
MIT
Slack MCP Server
Communication Search Developer Tools
paterapatera
A
license
Not graded
quality
D
maintenance
An MCP server that enables AI agents to search and retrieve messages within a Slack workspace using the Slack Web API. It supports specific channel filtering and includes built-in rate limit handling for efficient message discovery.
Updated 7 months ago (2026-02-19 00:22 UTC)
25 npm
MIT
agenthub MCP
Communication Agent Orchestration
thebusted
A
license
Not graded
quality
C
maintenance
A bearer-authed message hub for AI coding agents to communicate across machines and sessions, providing tools for sending, polling, and managing channels.
Updated 2 months ago (2026-07-15 11:17 UTC)
MIT

Appeared in Searches

A server for finding channels

Slack-MCP

📂 Folder Structure

🚀 Tools in This MCP

1. get_recent_messages

2. get_user_messages

3. summarize_recent_messages

4. group_messages_by_user

🚪 Slack OAuth Setup & Token Generation

1. Create a Slack App

2. Set OAuth Scopes

3. Install to Workspace

4. Save the Token

✨ Testing the Tools

On MCP Inspector (Local)

On Smithery (Cloud)

On Claude (Cloud Desktop)

🚜 Requirements

🔧 Environment File (.env)

🎉 Contributing

📹 Video Demo On claude desktop:

🙏 Acknowledgments

📊 Example Output

📊 Smithery.ai (Cloud Deployment)

🧑‍💻 Author

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches

1. `get_recent_messages`

2. `get_user_messages`

3. `summarize_recent_messages`

4. `group_messages_by_user`