A Python client library for the Model Context Protocol (MCP) that provides clean, async connectivity to MCP servers
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":"qv-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.
# QV MCP Client A Python client library for the Model Context Protocol (MCP) that provides clean, async connectivity to MCP servers. [](https://python.org) [](https://modelcontextprotocol.io) [](LICENSE) ## What is MCP? The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external data sources and tools. It provides a standardized way for AI models to interact with various systems including databases, file systems, APIs, and other services. ## Features - **Async Support**: Full async/await pattern for non-blocking operations - **Multiple Transports**: Support for stdio and HTTP-based connections - **Connection Management**: Built-in manager for handling multiple server connections - **Cross-Platform**: Windows-specific command handling included - **Error Handling**: Comprehensive exception hierarchy with detailed error information - **Type Safety**: Complete type hints throughout the codebase - **Modular Design**: Clean separation of concerns for easy maintenance ## Installation ```bash pip install mcp pip install -e . ``` ## Quick Start ### Basic Client Usage ```python import asyncio from qv_mcp_client import MCPClient, MCPServerConfig, MCPTransportType async def main(): config = MCPServerConfig( name="filesystem", transport=MCPTransportType.STDIO, command="npx", args=["-y", "@modelcontextprotocol/server-filesystem", "/tmp"] ) client = MCPClient() await client.connect(config) # List available tools tools = await client.list_tools() print(f"Available tools: {[tool['name'] for tool in tools]}") # Call a tool result = await client.call_tool("read_file", {"path": "/tmp/test.txt"}) print(f"Result: {result}") await client.disconnect() …
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.