302_custom_mcp

Created By
302aia year ago
在302后台自选Tools,快速生成定制的MCP Server。
Overview

what is 302 Custom MCP?

302 Custom MCP is a customizable server tool that allows users to quickly generate a tailored MCP (Model Context Protocol) server for various applications.

how to use 302 Custom MCP?

To use 302 Custom MCP, install the necessary dependencies, build the server, and configure it with your API key in the specified configuration file for your operating system.

key features of 302 Custom MCP?

  • Quick generation of custom MCP servers
  • Easy installation and configuration
  • Debugging tools available through MCP Inspector

use cases of 302 Custom MCP?

  1. Creating a custom server for AI applications.
  2. Integrating with Claude Desktop for enhanced functionality.
  3. Debugging and testing MCP servers using the MCP Inspector.

FAQ from 302 Custom MCP?

  • What is an MCP server?

An MCP server facilitates communication between AI models and applications using the Model Context Protocol.

  • How do I find my API key?

You can find your 302AI_API_KEY here.

  • Is there support for debugging?

Yes! You can use the MCP Inspector for debugging your MCP servers.

Server Config

{
  "mcpServers": {
    "302ai-custom-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@302ai/custom-mcp"
      ],
      "env": {
        "302AI_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
302ai
Star
-
Language
-
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)

11 hours ago