MCP Hub Project

Created By
CodeHalwella year ago
Repo to hold the code for the mcp server built in Gradio for the agents and mcp hackathon
Overview

What is the MCP Hub Project?

The MCP Hub Project is a sophisticated research assistant built using Gradio's Model Context Protocol (MCP) server functionality, designed to facilitate a workflow of interconnected AI agents for deep research capabilities.

How to use the MCP Hub Project?

To use the MCP Hub Project, clone the repository, set up a virtual environment, install the required dependencies, and run the main application. The Gradio interface will be accessible at http://127.0.0.1:7860/.

Key features of the MCP Hub Project?

  • MCP Server Implementation: Utilizes Gradio's MCP server for seamless agent communication.
  • Multi-Agent Architecture: Demonstrates interconnected agent services.
  • Real-time Web Search: Integrates with Tavily API for up-to-date information.
  • LLM Processing: Employs Nebius models for text processing.
  • Structured Workflow: Showcases a multi-step AI research process.
  • Citation Generation: Automatically formats APA-style citations from web sources.

Use cases of the MCP Hub Project?

  1. Enhancing user queries for better search results.
  2. Conducting comprehensive web searches for research purposes.
  3. Summarizing information from multiple sources into a cohesive answer.
  4. Generating citations for academic work.

FAQ from the MCP Hub Project?

  • What are the prerequisites for using the MCP Hub Project?

You need Python 3.12+, and API keys for Nebius and Tavily.

  • Is there a user interface available?

Yes, the Gradio interface provides an easy way to interact with the project.

  • Can I contribute to the MCP Hub Project?

Yes, contributions are welcome, and guidelines can be found in the repository.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
CodeHalwell
Star
0
Language
Python
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)

2 days ago