The official Slack MCP server enables AI agents to interact with Slack workspaces.
npx -y @modelcontextprotocol/server-slack
{
"mcpServers": {
"slack": {
"env": {
"SLACK_TEAM_ID": "T00000000",
"SLACK_BOT_TOKEN": "xoxb-your-token"
},
"args": [
"-y",
"@modelcontextprotocol/server-slack"
],
"command": "npx"
}
}
}Retrieve recent messages from a channel
{
"type": "object",
"required": [
"channel_id"
],
"properties": {
"limit": {
"type": "integer"
},
"channel_id": {
"type": "string"
}
}
}// Input
{
"limit": 5,
"channel_id": "C01"
}// Output
{
"messages": [
{
"text": "Ready for review?",
"user": "U01"
}
]
}List public channels in the workspace
{
"type": "object",
"properties": {
"limit": {
"type": "integer"
}
}
}// Input
{
"limit": 10
}// Output
{
"channels": [
{
"id": "C01",
"name": "general",
"num_members": 150
}
]
}Send a message to a Slack channel
The official Slack MCP server enables AI agents to interact with Slack workspaces.
Slack provides 4 tools including get_channel_history, list_channels, post_message, and 1 more.
Yes, Slack is completely free to use with no usage limits on the free tier.
You can install Slack using the following command: npx -y @modelcontextprotocol/server-slack. After installation, add the provided config snippet to your Claude Desktop or Cursor configuration.
{
"type": "object",
"required": [
"channel",
"text"
],
"properties": {
"text": {
"type": "string"
},
"channel": {
"type": "string"
}
}
}// Input
{
"text": "Deploy complete",
"channel": "C01"
}// Output
{
"ok": true,
"ts": "1678901234.567"
}Search messages across the workspace
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string"
}
}
}// Input
{
"query": "deployment error"
}// Output
{
"matches": [
{
"text": "Deploy error in staging"
}
]
}Slack is listed under the Communication category in the AgentForge MCP registry.
Slack has a current uptime of 99.9% with an average response time of 210ms.
To connect Slack, click the "Connect Agent" button on this page to get the configuration snippet. Add it to your MCP client (Claude Desktop, Cursor, or any MCP-compatible tool). Your AI agent will then have access to all of Slack's tools via the Model Context Protocol.