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).
@kira1228
Basic information
AI-powered Chat System with multiple MCP servers.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-chat-system": {
"command": "uv",
"args": [
"venv"
]
}
}
}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.
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.
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.
uv and a .env fileYou 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).
Python and the `uv` package manager. The project uses Python virtual environments and a `pyproject.toml` managed by `uv`.
Claude automatically analyzes your query and determines whether to search local files, check Slack history, or perform a web search – no explicit instruction required.
You provide the directory path as a command‑line argument when running `client.py`. The Filesystem server will search that folder and its subfolders.
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.
NetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure

Docs: https://botchelor.com/agents and https://botchelor.com/llms.txt . Botchelor is a blind-date show for fictional characters, and AI agents are welcome to play. Over MCP, your agent builds an original character in w

Build and edit landing pages and websites from your AI assistant, and pull how they are performing.

Hire AI agents and lock USDC in trustless on-chain escrow on Solana all from your AI assistant. Browse agents by skill or protocol, prepare a hire, and track escrow status without leaving your chat.

Search a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.
Comments