A comprehensive MCP client with direct connection and AI agent modes, including web interface
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"egile-mcp-client","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Egile MCP Client A comprehensive Model Context Protocol (MCP) client that provides two operational modes and a web interface for interacting with MCP servers. ## Features - **Two Operation Modes**: - **Direct Mode**: Connect directly to MCP server tools and resources - **Agent Mode**: Use a generic AI agent that works with any MCP server - **Multiple Interfaces**: - **Terminal CLI**: Command-line interface for both modes - **Web Chat Interface**: Browser-based chatbot with conversation history - **AI Provider Support**: OpenAI, Anthropic Claude, xAI Grok, and extensible for other providers - **Conversation History**: Persistent chat history across sessions - **Real-time Communication**: WebSocket support for live interactions ## Quick Start ### Installation ```bash # Install dependencies pip install -e . # Or using poetry poetry install ``` ### Configuration Create a `config.yaml` file: ```yaml # AI Providers (for agent mode) ai_providers: openai: api_key: "your-openai-api-key" model: "gpt-4" anthropic: api_key: "your-anthropic-api-key" model: "claude-3-sonnet-20240229" xai: api_key: "your-xai-api-key" model: "grok-3" # MCP Servers mcp_servers: - name: "example_server" url: "http://localhost:8000" type: "http" - name: "local_server" command: ["python", "/path/to/server/main.py"] type: "stdio" # Default settings default_ai_provider: "openai" web_interface: host: "localhost" port: 8080 ``` ### Usage #### Terminal Interface ```bash # Direct mode - connect directly to MCP server egile-mcp-client direct --server example_server # Agent mode - use AI agent with MCP tools egile-mcp-client agent --provider openai # List available tools from a server egile-mcp-client tools --server example_server # Interactive chat in terminal egile-mcp-client chat --mode agent --provider openai ``` #### Web Interface ```bash # Start the web server egile-mcp-client web # Then open http://localhost:8080 in yo…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.