Perplexity MCP Zerver

Created By
wysh3a year ago
MCP web search using perplexity without any API KEYS
Overview

What is Perplexity MCP Zerver?

Perplexity MCP Zerver is a research-level Model Context Protocol (MCP) server implementation that provides AI-powered research capabilities through Perplexity's infrastructure without the need for API keys.

How to use Perplexity MCP Zerver?

To use Perplexity MCP Zerver, clone the repository, install the dependencies, build the server, and configure it in your MCP settings. After setup, restart your IDE and interact with the server.

Key features of Perplexity MCP Zerver?

  • 🔍 Web search integration via Perplexity
  • 🔑 Use without any API Key
  • 🛠️ TypeScript-first implementation
  • 📦 Modular tool architecture

Use cases of Perplexity MCP Zerver?

  1. Conducting comprehensive web searches with adjustable detail levels.
  2. Retrieving up-to-date documentation and code examples.
  3. Discovering and evaluating APIs based on technical requirements.
  4. Analyzing code for deprecated patterns and providing migration guidance.
  5. Engaging in ongoing conversations with Perplexity AI.

FAQ from Perplexity MCP Zerver?

  • Can I use Perplexity MCP Zerver without an API key?

Yes! It is designed to work without any API keys.

  • What programming language is used in this project?

The project is implemented in TypeScript.

  • Is there any support for deprecated code analysis?

Yes, it includes a tool to check for deprecated code and provide migration guidance.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
wysh3
Star
33
Language
JavaScript
License
GPL-3.0 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