Provides tools for creating channels, inviting users, posting messages, replying in threads, pinning messages, and listing users in a Slack workspace.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Slack MCP Create a private channel called gtm-jeff and invite harper@2389.ai and dylan@2389.ai"
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 server for Slack workspace integration. Handles channel creation, user invites, message posting, and thread management.
Go to api.slack.com/apps
Click "Create New App" → "From scratch"
Name it (e.g., "Claude MCP") and select your workspace
Under "OAuth & Permissions", add these Bot Token Scopes:
channels:manage # create public channels
groups:write # create private channels
channels:read # list channels
groups:read # read private channels
chat:write # post messages
pins:write # pin messages
users:read # list users
users:read.email # lookup users by emailClick "Install to Workspace" and authorize the app.
Copy the "Bot User OAuth Token" (starts with xoxb-).
export SLACK_BOT_TOKEN="xoxb-your-token-here"Or add to your Claude config:
{
"mcpServers": {
"slack": {
"command": "node",
"args": ["/path/to/slack-mcp/dist/index.js"],
"env": {
"SLACK_BOT_TOKEN": "xoxb-your-token-here"
}
}
}
}npm install
npm run build
npm startRelated MCP server: Slack MCP Server
Create a new Slack channel.
{
"name": "gtm-jeff",
"is_private": true,
"description": "GTM materials for Jeff launch"
}Invite users by email or user ID.
{
"channel_id": "C123ABC",
"users": ["harper@2389.ai", "dylan@2389.ai"]
}Post a message to a channel.
{
"channel_id": "C123ABC",
"text": "## Email
**Subject:** meet jeff..."
}Reply to a message in a thread.
{
"channel_id": "C123ABC",
"thread_ts": "1234567890.123456",
"text": "Updated the subject line"
}Pin a message to a channel.
{
"channel_id": "C123ABC",
"message_ts": "1234567890.123456"
}List all users in the workspace.
{}After generating GTM materials, say "push to slack":
Creates #gtm-[product] private channel
Invites Harper and Dylan
Posts each output (email, blog, tweets) as separate messages
Pins the summary message
MIT
/plugin marketplace add 2389-research/claude-plugins
/plugin install slack-mcp@2389-researchIf Slack MCP saved you from context-switching out of your terminal, a ⭐ helps us know it's landing.
Built by 2389 · Part of the Claude Code plugin marketplace
Create a new Slack channel (public or private)
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Channel name (lowercase, no spaces). Will be normalized automatically. | |
| is_private | No | Whether the channel is private (default: true) | |
| description | No | Channel purpose/description (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It does not mention idempotency, error handling, permissions, or what happens on duplicate names. Minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is front-loaded and efficient, earning its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with 3 parameters and no output schema, but the description omits return value, error scenarios, and prerequisites. Adequate but not fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema descriptions already explain normalization, defaults, and optionality. The tool description adds no extra semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'create' and resource 'Slack channel' and specifies public/private. It effectively distinguishes from sibling tools like slack_invite_to_channel, slack_post_message, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance is provided. The description implies usage for creating channels but lacks alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Invite users to a Slack channel by email or user ID
| Name | Required | Description | Default |
|---|---|---|---|
| channel_id | Yes | The channel ID to invite users to | |
| users | Yes | Array of user emails or user IDs to invite |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It fails to disclose important behavioral aspects like permissions required, behavior if users are already in the channel, rate limits, or confirmation of success. The description is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (10 words) that front-loads the core purpose. No wasted words; all information is relevant.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 string params, no output schema), the description is adequate but lacks details on return format, edge cases, or authorization requirements. It could be more complete for a tool that modifies state.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters having descriptions. The description adds the phrase 'by email or user ID' which reinforces but does not significantly extend beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (invite users) and the resource (Slack channel), and specifies the identification methods (email or user ID). It effectively distinguishes from sibling tools like slack_create_channel or slack_post_message.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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, such as prerequisites (e.g., channel membership), or conditions under which invitation might fail. No explicit context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all users in the Slack workspace for user ID lookup
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It indicates a read-only list operation but does not disclose potential size of results, pagination, or response structure. Minimal but adequate for a simple tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no redundant information. It front-loads the action and purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless tool with no output schema, the description provides sufficient context to understand its purpose. No additional information is needed for basic usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the description does not need to add parameter-specific information. Baseline of 4 is appropriate as no additional semantic value is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (List), resource (all users), scope (in the Slack workspace), and purpose (for user ID lookup). It is specific and distinguishes from sibling tools which are unrelated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when needing user IDs but does not explicitly state when to use versus alternatives or provide exclusion criteria. Siblings are unrelated, so context is clear but guidance is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pin a message to a channel
| Name | Required | Description | Default |
|---|---|---|---|
| channel_id | Yes | The channel ID containing the message | |
| message_ts | Yes | Timestamp of the message to pin |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description fails to disclose key behavioral traits like whether pinning replaces existing pins, if it is idempotent, or if it triggers notifications. For a mutation tool, more context is needed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, concise sentence that contains no superfluous information. Every word is necessary and impactful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with only two parameters, but there is no output schema and no mention of return behavior (success/failure). While minimal, it lacks guidance on usage context relative to sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear descriptions for both channel_id and message_ts. The description adds no extra meaning beyond the schema, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (pin) and the resource (a message to a channel). It distinguishes from siblings like slack_post_message and slack_post_thread, which involve posting rather than pinning.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 (e.g., pinning versus reposting). There is no mention of prerequisites such as requiring an existing message or proper permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Post a message to a Slack channel. Supports markdown formatting.
| Name | Required | Description | Default |
|---|---|---|---|
| channel_id | Yes | The channel ID to post to | |
| text | Yes | Message content (markdown supported) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It only mentions markdown support, but does not disclose side effects, authentication needs, rate limits, or what happens on success/failure. The behavioral transparency is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with two sentences, no superfluous information, and directly addresses the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should compensate by explaining return values, error handling, or permissions. It lacks this context, making it incomplete for an agent to fully anticipate the tool's behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds context by stating markdown support applies to the text parameter, but does not elaborate on channel_id beyond what the schema provides. Overall, limited added value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Post a message to a Slack channel' and mentions markdown support. However, it does not explicitly distinguish from sibling tool slack_post_thread, which posts to a thread rather than a channel.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance provided on when to use this tool versus alternatives like slack_post_thread or slack_pin_message. The description does not mention any prerequisites or context for its use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reply to a message in a thread
| Name | Required | Description | Default |
|---|---|---|---|
| channel_id | Yes | The channel ID containing the thread | |
| thread_ts | Yes | Timestamp of the parent message to reply to | |
| text | Yes | Reply content (markdown supported) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided and description lacks behavioral details (e.g., thread existence requirements, error cases), leaving the agent to guess.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words; adequately describes the core action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 3-parameter tool, the description is minimally adequate, but lacks return value details and usage context beyond the action.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers all parameters with descriptions, so description adds no extra meaning. Baseline 3 applies due to full schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'Reply' and resource 'message in a thread', effectively differentiating from siblings like slack_post_message which posts to a channel.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance; agents must infer from sibling tool names. Could mention alternatives for top-level posting.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Each tool targets a distinct action: creating channels, inviting users, listing users, pinning messages, posting messages, and replying in threads. No overlap in purpose.
All tools follow a consistent 'slack_verb_noun' pattern in snake_case, making them predictable and easy to differentiate.
With 6 tools, the set is concise and covers essential Slack operations without being overly large or sparse.
Missing critical operations like reading messages, listing channels, editing/deleting messages, and direct messaging, which limits the server's utility for typical Slack workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Enable interaction with Slack workspaces. Supports subscribing to Slack events through Resources.
Manage projects, tasks, time tracking, and team collaboration through natural language.
Draft, schedule, and publish social posts for your workspace straight from your AI.
Schedule and manage Google Calendar events directly from your workspace. Check availability, view…
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/2389-research/slack-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
