Open Source MCP CLient Library

Created By
bittush8789a year ago
Overview

What is MCP-Use?

MCP-Use is an open-source library that allows developers to connect any Large Language Model (LLM) to MCP tools, enabling the creation of custom agents with tool access without relying on closed-source applications.

How to use MCP-Use?

To use MCP-Use, install it via pip and set up your environment with the necessary API keys for your chosen LLM provider. You can create an agent with just a few lines of code and run queries using the agent.

Key features of MCP-Use?

  • Ease of use: Create an MCP capable agent with only 6 lines of code.
  • LLM Flexibility: Compatible with any LangChain supported LLM that supports tool calling.
  • HTTP Support: Connect directly to MCP servers running on specific HTTP ports.
  • Multi-Server Support: Use multiple MCP servers simultaneously in a single agent.
  • Tool Restrictions: Control access to potentially dangerous tools like file system or network access.

Use cases of MCP-Use?

  1. Web browsing with Playwright.
  2. Searching for accommodations on Airbnb.
  3. Creating 3D models using Blender.
  4. Running complex queries that require multiple tools from different servers.

FAQ from MCP-Use?

  • Can MCP-Use connect to any LLM?
    Yes, it works with any LLM that supports tool calling through LangChain.

  • Is MCP-Use free to use?
    Yes, MCP-Use is open-source and free for everyone.

  • What are the requirements for using MCP-Use?
    You need Python 3.11+, an MCP implementation, and the appropriate LangChain model libraries.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
bittush8789
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