MCP-Codex: Model Context Protocol Tool Orchestration

Created By
twolvena year ago
A MCP server for calling MCP tools remotely without requiring installation.
Overview

What is MCP-Codex?

MCP-Codex is a Model Context Protocol (MCP) server designed for orchestrating tools remotely without the need for installation, allowing AI assistants to dynamically discover and utilize tools.

How to use MCP-Codex?

To use MCP-Codex, clone the repository, install the required dependencies, and start the Codex service and MCP client. The client allows AI assistants to search for and execute tools on demand.

Key features of MCP-Codex?

  • Intelligent tool discovery through 'The Librarian' agent.
  • Dynamic tool management without requiring restarts.
  • Remote execution of tools across different environments.
  • Centralized management of tool configurations.

Use cases of MCP-Codex?

  1. Enabling AI assistants to access a variety of tools without manual configuration.
  2. Facilitating real-time tool installation and execution based on user queries.
  3. Supporting complex workflows that require multiple tools to be used in sequence.

FAQ from MCP-Codex?

  • Is MCP-Codex still actively developed?

No, the project was discontinued after Cloudflare released a similar service. However, it remains a valuable educational resource.

  • What programming language is used?

MCP-Codex is developed in Python.

  • Can I still use MCP-Codex for my projects?

Yes, you can use the codebase as a reference for understanding MCP orchestration.

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