Happy slice of mcp pizzaMCP.pizza

slack-mcp-client

MCP.Pizza Chef: tuannvm

Install it and your team talks to an AI inside Slack that can genuinely reach files, databases, code repositories, and servers through whichever add-ons you point it at, with each thread keeping its own memory. One catch matters a lot: the author has archived the project, so it is frozen, takes no further fixes, and names no successor. Running it also means creating a Slack app with two tokens, paying for an OpenAI or Anthropic key or hosting a local model, and deploying with Docker or Kubernetes.

Archived · author archived the repository; no successor named
Coding
Communication

Use This MCP client To

Ask a question in Slack and get an answer from real data Let teammates run tools without leaving Slack Check whether a server is healthy from a thread Search our internal notes from a channel Summarize a file for the team in Slack

README

Slack MCP Client

A production-ready bridge between Slack and AI models with full MCP compatibility.

This client enables AI models (OpenAI GPT-4.1, Anthropic Claude 4.5, Ollama local models) to interact with real tools and systems through Slack conversations. Built on the industry-standard Model Context Protocol (MCP), it provides secure access to filesystems, databases, Kubernetes clusters, Git repositories, and custom tools.

GitHub Workflow Status Go Version Trivy Scan Docker Image GitHub Release License: MIT

Compatible with MCP Specification 2025-06-18 - Compliant with the latest Model Context Protocol standards

Recent Updates

Oct 2025: langchaingo v0.1.14 with streaming fixes, enhanced agent parsing, and API key sanitization.

Key Features

  • Universal MCP Compatibility - Supports all transport methods (HTTP, SSE, stdio)
  • Multi-Provider LLM Support - OpenAI GPT-4.1/4o, Anthropic Claude 4.5, Ollama (Llama 3.3, Qwen, Mistral, DeepSeek)
  • Agent Mode - Multi-step reasoning with LangChain for complex workflows
  • RAG Integration - Knowledge base with semantic search capabilities
  • Thread-Aware Context - Maintains separate conversation history per Slack thread
  • User Context Integration - Personalized responses with cached user information
  • Unique Tool Naming - Server-prefixed tool names prevent conflicts across MCP servers
  • Production Ready - Comprehensive configuration, monitoring, and security

slack-mcp-client FAQ

Is this still maintained?
No. The author archived the project, so it is frozen and accepts no fixes or new features. Nothing is named as a replacement, so treat it as a snapshot in time.
What does it cost to run?
The bot itself is free, but it needs a paid OpenAI or Anthropic key billed by usage, unless you run a local model with Ollama instead.
Can I use this to let my team query a database from Slack?
Yes, provided you point it at an add-on that reaches that database. Slack becomes the front door for whatever tools you connect.
Do I need to be a Slack administrator?
In practice yes. Someone has to create a Slack app, switch on the connection mode it relies on, and copy out two tokens before it will start.
How hard is setup?
This is real work. Expect a Slack app, a config file, and running it as a container or on a Kubernetes cluster using the supplied chart.
Which chat apps does it plug into?
None of them. It is the assistant itself — it runs its own model, connects to add-ons directly, and uses Slack as the place people type.
Does each conversation stay separate?
Yes. Every Slack thread carries its own history, so two people can hold unrelated conversations with the bot at the same time.
Is it safe to rely on now that it is frozen?
The description still calls it production-ready, but an archived project receives no security updates. If you depend on it, plan to fork and maintain it yourself.