What can Slack MCP Server do?

slack workspace channel enumeration and metadata retrieval, slack message history retrieval with thread context, slack message posting with channel targeting, slack thread reply composition and posting, slack message reaction management (add/remove emoji reactions), mcp tool schema registration and json-rpc transport, slack bot token authentication and scope validation, slack api error handling and rate limit management

Slack MCP Server

MCP ServerFree

Read and send Slack messages and manage channels via MCP.

Open Source

/ 100

8 capabilities

Capabilities8 decomposed

slack workspace channel enumeration and metadata retrieval

Medium confidence

Exposes an MCP tool that queries the Slack API to list all accessible channels in a workspace, returning channel IDs, names, topics, and membership counts. Implements standardized MCP tool schema with JSON-RPC transport, allowing LLM clients to discover and inspect channel structure without direct API knowledge. Handles pagination and permission-based filtering automatically through Slack API responses.

Solves for

I need my AI agent to understand what channels exist in my Slack workspace before deciding where to postI want to programmatically discover channel metadata to route messages to the right conversationI need to list only channels the authenticated user has access to

Best for

AI agents and assistants integrated with Slack workspaces

Teams building Slack-aware chatbots that need workspace awareness

Developers creating Slack automation workflows with LLM decision-making

Requires

Slack workspace with bot token having 'channels:read' scope

MCP client implementation (Claude, custom LLM application, etc.)

Network connectivity to Slack API endpoints

Limitations

Returns only channels accessible to the authenticated bot token — private channels require explicit membership

No filtering by channel type (public vs private) in the tool itself — clients must parse response

Pagination handled transparently but large workspaces (1000+ channels) may incur multiple API calls with latency impact

What makes it unique

Implements channel enumeration as a first-class MCP tool primitive rather than requiring clients to call Slack API directly, enabling LLM-native reasoning about workspace structure through standardized tool schema and JSON-RPC transport

vs alternatives

Simpler than building custom Slack API wrappers because it leverages MCP's standardized tool registry and transport, making it immediately available to any MCP-compatible LLM client without additional SDK integration

slack message history retrieval with thread context

Medium confidence

Implements an MCP tool that fetches message history from a specified Slack channel, returning messages with timestamps, authors, and thread metadata. Uses Slack's conversations.history API endpoint with configurable limit and cursor-based pagination. Preserves thread relationships and reply counts, enabling LLM clients to understand conversation context and thread structure without flattening message hierarchy.

Solves for

I want my AI assistant to read recent messages in a channel to understand ongoing discussionsI need to fetch message history for analysis or summarization by an LLMI want to retrieve messages with full thread context to maintain conversation coherence

Best for

Slack-integrated AI assistants that need conversation context before responding

Teams building message analysis or summarization agents

Developers creating Slack bots that must understand historical context

Requires

Slack bot token with 'channels:history' scope

Valid channel ID (not channel name)

MCP client with tool-calling capability

Limitations

Default limit typically 100 messages per call — requires pagination for longer histories

Thread replies are not automatically expanded — clients must make separate API calls per thread

Message content is returned as-is without parsing mentions, links, or file attachments into structured format

What makes it unique

Exposes Slack message history as an MCP tool with built-in pagination support and thread metadata preservation, allowing LLM clients to maintain conversation context without manually managing Slack API cursors or thread expansion logic

vs alternatives

More context-aware than simple REST API wrappers because it preserves thread relationships and integrates with MCP's tool schema, enabling LLMs to reason about message structure natively

slack message posting with channel targeting

Medium confidence

Implements an MCP tool that sends messages to a specified Slack channel using the chat.postMessage API. Accepts message text and channel ID as parameters, handles Slack's message formatting (plain text, markdown-like syntax), and returns the posted message timestamp for reference. Integrates with MCP's tool-calling protocol to enable LLM-driven message composition and delivery without requiring clients to manage Slack API authentication.

Solves for

I want my AI agent to post notifications or summaries to a Slack channelI need to send messages composed by an LLM to specific channels programmaticallyI want to enable an AI assistant to communicate back to Slack users

Best for

AI agents and chatbots that need to send messages to Slack channels

Notification systems powered by LLMs

Teams building Slack-integrated workflow automation with AI decision-making

Requires

Slack bot token with 'chat:write' scope

Valid channel ID (bot must be a member of the channel)

MCP client with tool-calling capability

Limitations

Supports plain text and basic markdown formatting only — no rich block kit layouts or interactive elements

No built-in message threading — replies to threads require separate thread_ts parameter

No message editing or deletion capability — posted messages are immutable through this tool

What makes it unique

Wraps Slack's chat.postMessage API as an MCP tool primitive, enabling LLM clients to compose and send messages through standardized tool schema without direct API integration, with automatic authentication handling via bot token

vs alternatives

Simpler than building custom Slack SDKs because it abstracts authentication and API details into a single MCP tool, making message posting immediately available to any LLM client without SDK dependencies

slack thread reply composition and posting

Medium confidence

Implements an MCP tool that posts replies to existing Slack message threads using the chat.postMessage API with thread_ts parameter. Accepts channel ID, thread timestamp, and reply text, maintaining thread coherence by linking replies to parent messages. Enables LLM clients to participate in threaded conversations without flattening message hierarchy or losing conversation context.

Solves for

I want my AI assistant to reply to a specific message thread in SlackI need to keep AI-generated responses organized within existing conversation threadsI want to enable an LLM to participate in threaded discussions without breaking conversation flow

Best for

Slack-integrated AI assistants that need to maintain conversation threading

Teams building collaborative AI agents that participate in Slack discussions

Developers creating Slack bots that must preserve message hierarchy

Requires

Slack bot token with 'chat:write' scope

Valid channel ID and thread_ts from parent message

MCP client with tool-calling capability

Limitations

Requires valid thread_ts (parent message timestamp) — cannot create new threads, only reply to existing ones

No support for nested thread replies — all replies attach to the parent message, not intermediate replies

Thread visibility depends on channel permissions — private channels require explicit membership

What makes it unique

Exposes Slack's thread reply capability as a dedicated MCP tool, enabling LLM clients to maintain conversation threading natively without requiring manual thread_ts parameter management or API-level thread handling

vs alternatives

Preserves conversation structure better than generic message posting because it explicitly targets threads, allowing LLMs to reason about message hierarchy and maintain coherent multi-turn discussions

slack message reaction management (add/remove emoji reactions)

Medium confidence

Implements MCP tools for adding and removing emoji reactions to Slack messages. Uses the reactions.add and reactions.remove API endpoints, accepting message timestamp, channel ID, and emoji name as parameters. Enables LLM clients to express sentiment, acknowledgment, or categorization through Slack's native reaction system without direct API calls, integrating reaction management into agent workflows.

Solves for

I want my AI agent to acknowledge messages with emoji reactionsI need to categorize or tag messages using Slack reactions programmaticallyI want to enable an LLM to express sentiment or status through reactions

Best for

AI agents that need to provide lightweight feedback through reactions

Slack bots that categorize or triage messages with emoji tags

Teams building sentiment analysis or message classification workflows

Requires

Slack bot token with 'reactions:write' scope

Valid channel ID, message timestamp (ts), and emoji name

MCP client with tool-calling capability

Limitations

Emoji names must match Slack's internal emoji naming (e.g., 'thumbsup' not '👍') — no unicode emoji support

Cannot add reactions to messages in channels the bot is not a member of

No bulk reaction operations — each reaction requires a separate API call

What makes it unique

Wraps Slack's reactions API as MCP tools, enabling LLM clients to use emoji reactions as a lightweight feedback mechanism without requiring knowledge of Slack's internal emoji naming conventions or API endpoints

vs alternatives

More intuitive than building custom reaction handlers because it leverages Slack's native reaction system, allowing LLMs to express intent through familiar UI elements that Slack users already understand

mcp tool schema registration and json-rpc transport

Medium confidence

Implements the foundational MCP server infrastructure that registers all Slack tools (channel listing, message retrieval, posting, reactions) as standardized tool primitives with JSON schema definitions. Uses JSON-RPC 2.0 protocol over stdio or network transport to communicate tool availability and handle tool invocation requests from MCP clients. Manages authentication via Slack bot token and translates between MCP tool calls and Slack API requests.

Solves for

I want to expose Slack capabilities to any MCP-compatible LLM client without custom integrationI need a standardized way for AI agents to discover and invoke Slack toolsI want to decouple my LLM application from Slack API details through MCP abstraction

Best for

Developers building MCP-compatible LLM applications that need Slack integration

Teams deploying AI agents across multiple MCP clients (Claude, custom applications)

Organizations standardizing on MCP for tool integration across their AI stack

Requires

MCP client library (e.g., Claude SDK, custom MCP client implementation)

Slack bot token with appropriate scopes (channels:read, chat:write, reactions:write)

Node.js 18+ runtime for TypeScript server implementation

Limitations

Requires MCP client implementation — not compatible with non-MCP LLM applications

Tool schema is fixed at server startup — no dynamic tool registration or runtime schema updates

JSON-RPC transport adds ~50-200ms latency per tool invocation compared to direct API calls

What makes it unique

Implements the complete MCP server lifecycle including tool schema registration, JSON-RPC message handling, and Slack API translation, following the official MCP reference server pattern from modelcontextprotocol/servers repository

vs alternatives

More standardized than custom Slack API wrappers because it adheres to MCP protocol specifications, enabling interoperability with any MCP-compatible client and reducing vendor lock-in to specific LLM platforms

slack bot token authentication and scope validation

Medium confidence

Manages Slack bot token authentication by validating token format, checking required OAuth scopes (channels:read, chat:write, reactions:write), and handling token refresh if needed. Stores token securely and validates scope availability before executing tools, preventing runtime failures due to insufficient permissions. Implements error handling for invalid or expired tokens with clear error messages to clients.

Solves for

I want to ensure my Slack integration only uses tokens with required permissionsI need to validate that a bot token has access to perform specific actions before attempting themI want to handle token expiration gracefully without breaking agent workflows

Best for

Teams deploying Slack MCP servers in production environments

Developers building multi-workspace Slack integrations with varying permissions

Organizations requiring audit trails of which scopes are used

Requires

Valid Slack bot token (xoxb-* format)

Token must have been granted required scopes during OAuth flow

Environment variable or configuration mechanism to pass token to server

Limitations

No automatic token refresh — requires manual token rotation or external refresh mechanism

Scope validation happens at tool invocation time, not at server startup — missing scopes discovered during execution

No support for user tokens — only bot tokens with workspace-level scopes

What makes it unique

Implements scope-aware authentication that validates token permissions before tool execution, preventing silent failures and providing clear error messages when tools lack required OAuth scopes

vs alternatives

More secure than passing raw tokens to clients because it centralizes authentication in the MCP server and validates scopes server-side, reducing the risk of unauthorized API calls

slack api error handling and rate limit management

Medium confidence

Implements error handling for Slack API responses, translating Slack-specific errors (invalid_channel, not_in_channel, rate_limited) into MCP error protocol messages. Detects rate limiting (429 responses) and implements exponential backoff retry logic with configurable delays. Provides detailed error context to clients including error codes, descriptions, and retry suggestions, enabling graceful degradation in agent workflows.

Solves for

I want my AI agent to handle Slack API errors gracefully without crashingI need to implement retry logic when hitting Slack rate limitsI want clear error messages that help debug why a Slack operation failed

Best for

Production Slack MCP deployments handling high-volume tool invocations

Teams building resilient AI agents that must tolerate transient Slack API failures

Developers debugging Slack integration issues

Requires

MCP client that implements error handling for tool invocation failures

Slack API rate limit headers in responses

Limitations

Retry logic is server-side only — clients cannot customize backoff strategies

Rate limit detection relies on Slack API response headers — no proactive rate limit prediction

Exponential backoff may add significant latency (up to 30+ seconds) for heavily rate-limited scenarios

What makes it unique

Implements Slack-specific error translation and rate limit handling within the MCP server, abstracting API-level failures from clients and providing automatic retry logic with exponential backoff

vs alternatives

More resilient than naive API wrappers because it implements server-side retry logic and rate limit detection, preventing client-side cascading failures during Slack API throttling

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with Slack MCP Server, ranked by overlap. Discovered automatically through the match graph.

MCP Server42

slack-mcp-server

Model Context Protocol (MCP) server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins

slack workspace message retrieval and search via mcpthread-aware message context retrievalslack channel and user metadata exposure via mcp resourcesslack message posting and thread reply via mcp tools

4 shared capabilities

MCP Server28

@sigmacomputing/slack-mcp-server

MCP server for interacting with Slack

slack channel and conversation retrieval via mcp resourcesslack thread and reply managementslack user and workspace metadata lookup

3 shared capabilities

MCP Server31

@sigmacomputing/slack-mcp-server

MCP server for interacting with Slack

slack channel and user lookup with context retrievalslack thread management and repliesslack conversation history retrieval with pagination

3 shared capabilities

MCP Server29

slack-relay-mcp

Code-execution-based Slack MCP tool — CLI + TypeScript API + Claude Code skill

message pagination and history retrieval with filteringcli-based slack message sending and retrievalmcp resource exposure for slack channels and messages

3 shared capabilities

MCP Server23

Slack

** - Channel management and messaging capabilities. Now maintained by [Zencoder](https://github.com/zencoderai/slack-mcp-server)

slack channel listing and metadata retrievalslack conversation history retrieval with context windowing

2 shared capabilities

Product18

Q, ChatGPT for Slack

AI workforce on Slack for under-resourced SMEs

multi-channel message routing and context awarenessthreaded conversation persistence and reply management

2 shared capabilities

Best For

✓AI agents and assistants integrated with Slack workspaces
✓Teams building Slack-aware chatbots that need workspace awareness
✓Developers creating Slack automation workflows with LLM decision-making
✓Slack-integrated AI assistants that need conversation context before responding
✓Teams building message analysis or summarization agents
✓Developers creating Slack bots that must understand historical context
✓AI agents and chatbots that need to send messages to Slack channels
✓Notification systems powered by LLMs

Known Limitations

⚠Returns only channels accessible to the authenticated bot token — private channels require explicit membership
⚠No filtering by channel type (public vs private) in the tool itself — clients must parse response
⚠Pagination handled transparently but large workspaces (1000+ channels) may incur multiple API calls with latency impact
⚠Default limit typically 100 messages per call — requires pagination for longer histories
⚠Thread replies are not automatically expanded — clients must make separate API calls per thread
⚠Message content is returned as-is without parsing mentions, links, or file attachments into structured format

Requirements

Slack workspace with bot token having 'channels:read' scopeMCP client implementation (Claude, custom LLM application, etc.)Network connectivity to Slack API endpointsSlack bot token with 'channels:history' scopeValid channel ID (not channel name)MCP client with tool-calling capabilitySlack bot token with 'chat:write' scopeValid channel ID (bot must be a member of the channel)

Input / Output

Accepts: none — tool takes no parameters, channel_id (string), limit (optional integer), cursor (optional string for pagination), channel_id (string), text (string, required message content), channel_id (string), thread_ts (string, parent message timestamp), text (string, reply content), channel_id (string), timestamp (string, message ts), emoji_name (string, e.g., 'thumbsup'), JSON-RPC 2.0 requests with method name and tool parameters, Slack bot token (string), Slack API error responses (HTTP status codes, error messages)

Produces: JSON array of channel objects with id, name, topic, num_members fields, JSON array of message objects with ts, user, text, thread_ts, reply_count fields, JSON object with ts (message timestamp), channel, ok (boolean success flag), JSON object with ts (reply message timestamp), thread_ts (parent timestamp), channel, ok (boolean), JSON object with ok (boolean success flag), error (optional error message), JSON-RPC 2.0 responses with tool result or error, Authentication status (boolean), scope list (array of strings), error messages (string), MCP error protocol messages with error code, description, and retry metadata

UnfragileRank

Adoption70%(30% weight)

Quality23%(25% weight)

Ecosystem52%(25% weight)

Match Graph10%(15% weight)

Freshness100%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

8 capabilities

Visit Slack MCP Server→

About

Official MCP server for Slack workspace integration. Exposes tools for listing channels, reading message history, posting messages, replying to threads, and managing reactions in Slack.

Alternatives to Slack MCP Server

YouTube MCP Server46MCP Server

Extract and analyze YouTube video transcripts via MCP.

Compare →

Vercel MCP Server46MCP Server

Manage Vercel deployments, projects, and domains via MCP.

Compare →

Todoist MCP Server46MCP Server

Create and manage Todoist tasks and projects via MCP.

Compare →

Telegram MCP Server46MCP Server

Send messages and manage Telegram chats and bots via MCP.

Compare →

Are you the builder of Slack MCP Server?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

seed developer essentials

Looking for something else?

Search →

Capabilities8 decomposed

slack workspace channel enumeration and metadata retrieval

Medium confidence

Solves for

Best for

AI agents and assistants integrated with Slack workspaces

Teams building Slack-aware chatbots that need workspace awareness

Developers creating Slack automation workflows with LLM decision-making

Requires

Slack workspace with bot token having 'channels:read' scope

MCP client implementation (Claude, custom LLM application, etc.)

Network connectivity to Slack API endpoints

Limitations

Returns only channels accessible to the authenticated bot token — private channels require explicit membership

No filtering by channel type (public vs private) in the tool itself — clients must parse response

Pagination handled transparently but large workspaces (1000+ channels) may incur multiple API calls with latency impact

What makes it unique

vs alternatives

slack message history retrieval with thread context

Medium confidence

Solves for

Best for

Slack-integrated AI assistants that need conversation context before responding

Teams building message analysis or summarization agents

Developers creating Slack bots that must understand historical context

Requires

Slack bot token with 'channels:history' scope

Valid channel ID (not channel name)

MCP client with tool-calling capability

Limitations

Default limit typically 100 messages per call — requires pagination for longer histories

Thread replies are not automatically expanded — clients must make separate API calls per thread

Message content is returned as-is without parsing mentions, links, or file attachments into structured format

What makes it unique

vs alternatives

More context-aware than simple REST API wrappers because it preserves thread relationships and integrates with MCP's tool schema, enabling LLMs to reason about message structure natively

slack message posting with channel targeting

Medium confidence

Solves for

Best for

AI agents and chatbots that need to send messages to Slack channels

Notification systems powered by LLMs

Teams building Slack-integrated workflow automation with AI decision-making

Requires

Slack bot token with 'chat:write' scope

Valid channel ID (bot must be a member of the channel)

MCP client with tool-calling capability

Limitations

Supports plain text and basic markdown formatting only — no rich block kit layouts or interactive elements

No built-in message threading — replies to threads require separate thread_ts parameter

No message editing or deletion capability — posted messages are immutable through this tool

What makes it unique

vs alternatives

slack thread reply composition and posting

Medium confidence

Solves for

Best for

Slack-integrated AI assistants that need to maintain conversation threading

Teams building collaborative AI agents that participate in Slack discussions

Developers creating Slack bots that must preserve message hierarchy

Requires

Slack bot token with 'chat:write' scope

Valid channel ID and thread_ts from parent message

MCP client with tool-calling capability

Limitations

Requires valid thread_ts (parent message timestamp) — cannot create new threads, only reply to existing ones

No support for nested thread replies — all replies attach to the parent message, not intermediate replies

Thread visibility depends on channel permissions — private channels require explicit membership

What makes it unique

vs alternatives

slack message reaction management (add/remove emoji reactions)

Medium confidence

Solves for

Best for

AI agents that need to provide lightweight feedback through reactions

Slack bots that categorize or triage messages with emoji tags

Teams building sentiment analysis or message classification workflows

Requires

Slack bot token with 'reactions:write' scope

Valid channel ID, message timestamp (ts), and emoji name

MCP client with tool-calling capability

Limitations

Emoji names must match Slack's internal emoji naming (e.g., 'thumbsup' not '👍') — no unicode emoji support

Cannot add reactions to messages in channels the bot is not a member of

No bulk reaction operations — each reaction requires a separate API call

What makes it unique

vs alternatives

mcp tool schema registration and json-rpc transport

Medium confidence

Solves for

Best for

Developers building MCP-compatible LLM applications that need Slack integration

Teams deploying AI agents across multiple MCP clients (Claude, custom applications)

Organizations standardizing on MCP for tool integration across their AI stack

Requires

MCP client library (e.g., Claude SDK, custom MCP client implementation)

Slack bot token with appropriate scopes (channels:read, chat:write, reactions:write)

Node.js 18+ runtime for TypeScript server implementation

Limitations

Requires MCP client implementation — not compatible with non-MCP LLM applications

Tool schema is fixed at server startup — no dynamic tool registration or runtime schema updates

JSON-RPC transport adds ~50-200ms latency per tool invocation compared to direct API calls

What makes it unique

vs alternatives

slack bot token authentication and scope validation

Medium confidence

Solves for

Best for

Teams deploying Slack MCP servers in production environments

Developers building multi-workspace Slack integrations with varying permissions

Organizations requiring audit trails of which scopes are used

Requires

Valid Slack bot token (xoxb-* format)

Token must have been granted required scopes during OAuth flow

Environment variable or configuration mechanism to pass token to server

Limitations

No automatic token refresh — requires manual token rotation or external refresh mechanism

Scope validation happens at tool invocation time, not at server startup — missing scopes discovered during execution

No support for user tokens — only bot tokens with workspace-level scopes

What makes it unique

Implements scope-aware authentication that validates token permissions before tool execution, preventing silent failures and providing clear error messages when tools lack required OAuth scopes

vs alternatives

More secure than passing raw tokens to clients because it centralizes authentication in the MCP server and validates scopes server-side, reducing the risk of unauthorized API calls

slack api error handling and rate limit management

Medium confidence

Solves for

Best for

Production Slack MCP deployments handling high-volume tool invocations

Teams building resilient AI agents that must tolerate transient Slack API failures

Developers debugging Slack integration issues

Requires

MCP client that implements error handling for tool invocation failures

Slack API rate limit headers in responses

Limitations

Retry logic is server-side only — clients cannot customize backoff strategies

Rate limit detection relies on Slack API response headers — no proactive rate limit prediction

Exponential backoff may add significant latency (up to 30+ seconds) for heavily rate-limited scenarios

What makes it unique

Implements Slack-specific error translation and rate limit handling within the MCP server, abstracting API-level failures from clients and providing automatic retry logic with exponential backoff

vs alternatives

More resilient than naive API wrappers because it implements server-side retry logic and rate limit detection, preventing client-side cascading failures during Slack API throttling

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to Slack MCP Server

YouTube MCP Server46MCP Server

Extract and analyze YouTube video transcripts via MCP.

Compare →

Vercel MCP Server46MCP Server

Manage Vercel deployments, projects, and domains via MCP.

Compare →

Todoist MCP Server46MCP Server

Create and manage Todoist tasks and projects via MCP.

Compare →

Telegram MCP Server46MCP Server

Send messages and manage Telegram chats and bots via MCP.

Compare →

Slack MCP Server

Capabilities8 decomposed

slack workspace channel enumeration and metadata retrieval

slack message history retrieval with thread context

slack message posting with channel targeting

slack thread reply composition and posting

slack message reaction management (add/remove emoji reactions)

mcp tool schema registration and json-rpc transport

slack bot token authentication and scope validation

slack api error handling and rate limit management

Related Artifactssharing capabilities

slack-mcp-server

@sigmacomputing/slack-mcp-server

@sigmacomputing/slack-mcp-server

slack-relay-mcp

Slack

Q, ChatGPT for Slack

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Slack MCP Server

Are you the builder of Slack MCP Server?

Get the weekly brief

Data Sources

Slack MCP Server

Capabilities8 decomposed

slack workspace channel enumeration and metadata retrieval

slack message history retrieval with thread context

slack message posting with channel targeting

slack thread reply composition and posting

slack message reaction management (add/remove emoji reactions)

mcp tool schema registration and json-rpc transport

slack bot token authentication and scope validation

slack api error handling and rate limit management

Related Artifactssharing capabilities

slack-mcp-server

@sigmacomputing/slack-mcp-server

@sigmacomputing/slack-mcp-server

slack-relay-mcp

Slack

Q, ChatGPT for Slack

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

About

Categories

Alternatives to Slack MCP Server

Are you the builder of Slack MCP Server?

Get the weekly brief

Data Sources