Advertise
MCP.so
Sign In

AI-powered chat system with multiple MCP servers.

@kira1228

Repository

Basic information

Category

AI & Agents

License

MIT

Transports

stdio

Author

kira1228

About AI-powered chat system with multiple MCP servers.

AI-powered Chat System with multiple MCP servers.

AI-powered chat system with multiple MCP servers. config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-chat-system": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

AI-powered chat system with multiple MCP servers. tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is AI-powered chat system with multiple MCP servers.?

This system is a client‑server architecture based on the Model Context Protocol (MCP). It connects a host application (Claude) with three specialized MCP servers: Filesystem (access local folders), Slack (access workspace conversations), and Brave‑Search (real‑time web search). It is intended for users who want to query local files, Slack history, and the web through a single AI interface.

How to use AI-powered chat system with multiple MCP servers.?

Install the uv package manager, clone the repository, create a .env file with your API keys (ANTHROPIC_API_KEY, SLACK_BOT_TOKEN, SLACK_TEAM_ID, BRAVE_API_KEY), create a virtual environment with uv venv, activate it, and install dependencies with uv sync. Run the client with uv run client.py path/to/dir/you/want/to/use. The system automatically selects the appropriate MCP server based on your query.

Key features of AI-powered chat system with multiple MCP servers.

  • Supports three MCP servers: Filesystem, Slack, and Brave‑Search
  • Intelligent routing – Claude chooses the server automatically
  • Works with local file directories, Slack workspaces, and web search
  • Requires minimal setup with uv and a .env file
  • Follows the MCP client‑server architecture
  • Open source under the MIT License

Use cases of AI-powered chat system with multiple MCP servers.

  • Search and retrieve information from your local documents and folders
  • Access and reference Slack conversations, channels, and shared resources
  • Perform real‑time web searches to incorporate the latest online information
  • Combine local, team, and web data in a single AI chat session

Frequently asked questions

1

What API keys are required?

You need four keys: `ANTHROPIC_API_KEY` (for Claude), `SLACK_BOT_TOKEN` and `SLACK_TEAM_ID` (for Slack integration), and `BRAVE_API_KEY` (for Brave web search).

2

What runtime and dependencies are needed?

Python and the `uv` package manager. The project uses Python virtual environments and a `pyproject.toml` managed by `uv`.

3

How does the system decide which server to use?

Claude automatically analyzes your query and determines whether to search local files, check Slack history, or perform a web search – no explicit instruction required.

4

Where should I place the files I want to search?

You provide the directory path as a command‑line argument when running `client.py`. The Filesystem server will search that folder and its subfolders.

5

What transport or authentication does the system use?

The client runs locally over stdio. Authentication is handled via environment variables (API keys and tokens); no additional transport configuration is described in the README.

Comments

More AI & Agents MCP servers

早

早起鸟儿喊真人验真

shenshaoyin

早起鸟儿喊真人验真 is a remote MCP server available at http://121.40.18.232.

F

fhirHydrant

faulkj

Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

14

KissCode

NickSF189

KissCode is the world's first relationship network where AI agents and people meet. Connect your agent over MCP: it gets a profile, meets other agents and real people, chats, sends virtual gifts, goes on dinner and movie

F

Factanker

FACTANKER serves 1.18B+ evidence-backed facts about US companies, banks, nonprofits and federal spending, sourced from SEC EDGAR, FFIEC call reports, IRS 990 filings and USAspending. Every value carries its evidence: fil

BlazingCDN MCP - Content Delivery for Video, Software & Static Files

BlazingCDN

Official MCP server for BlazingCDN - AI agents (Claude, Cursor, Windsurf) manage CDN resources, purge cache, query metrics, domains, Anycast CDN, Video CDN and Media CDN

1
Advertise