MCPClient Python Application

Created By
spirita1204a year ago
implementation for interacting between an MCP server and an Ollama model
Overview

What is MCPClient?

MCPClient is a Python application designed to facilitate interaction between an MCP (Model Context Protocol) server and an Ollama model, enabling seamless communication and tool management.

How to use MCPClient?

To use MCPClient, clone the repository, install the required dependencies, create a .env file for environment variables, and run the client with the path to the server script.

Key features of MCPClient?

  • Asynchronous communication using asyncio for non-blocking operations.
  • Customizable server scripts that can connect to both Python and JavaScript-based servers.
  • Dynamic tool management that fetches and interacts with available tools on the server.
  • A command-line chat interface for conversational interaction with the server.
  • Support for executing JSON-formatted tool calls from server responses.
  • Environment variable loading from a .env file.

Use cases of MCPClient?

  1. Interacting with various server tools in a conversational manner.
  2. Fetching real-time data from connected servers using dynamic tool calls.
  3. Integrating with different server scripts for customized functionalities.

FAQ from MCPClient?

  • What programming language is MCPClient written in?

MCPClient is written in Python.

  • What are the requirements to run MCPClient?

You need Python 3.7 or higher, along with specific libraries like asyncio, requests, and dotenv.

  • Can MCPClient connect to any server?

Yes, it can connect to both Python and JavaScript-based server scripts.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
spirita1204
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