Slack MCP Host

Created By
jexpa year ago
MCP Host Server Application for Slack
Overview

What is Slack MCP Host?

Slack MCP Host is a Slack bot that integrates Machine Control Protocol (MCP) servers with Slack, enabling users to interact with these servers through LLM-powered conversations in dedicated channels.

How to use Slack MCP Host?

To use Slack MCP Host, set up the bot by cloning the repository, configuring your environment with necessary credentials, and deploying it to your Slack workspace. Users can then interact with the bot to execute commands on MCP servers.

Key features of Slack MCP Host?

  • LLM-powered conversations in Slack
  • Integration with multiple MCP servers
  • Markdown rendering support for tool results
  • Collapsible tool execution results for better readability
  • Maintenance of conversation history
  • Secure configuration management for sensitive data

Use cases of Slack MCP Host?

  1. Finding movies directed by specific filmmakers using a Neo4j database.
  2. Executing various commands on MCP servers directly from Slack.
  3. Facilitating team discussions around data retrieved from MCP servers.

FAQ from Slack MCP Host?

  • What is required to run Slack MCP Host?

    You need Python 3.11+, a Slack workspace with admin access, OpenAI API access, and one or more MCP servers.

  • Is there a cost associated with using Slack MCP Host?

    Slack MCP Host is free to use, but you may incur costs from the OpenAI API depending on your usage.

  • Can I customize the bot's functionality?

    Yes! You can modify the bot's code and add new features as needed.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
jexp
Star
0
Language
Python
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago