Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Perplexity web search and research
Perplexity MCP Zerver connects an MCP client to Perplexity through browser automation, so your agent can search, summarize, and retrieve documentation without API keys. It stores chat history locally and supports GitHub-aware content extraction and developer-oriented lookup tools.
Builders who want an MCP-compatible agent to do research, fetch docs, and inspect code through Perplexity’s web interface.
You can give your agent web research and documentation tools without managing API keys.
What it does
Web search
Runs research queries through Perplexity and returns raw text results.
Documentation retrieval
Fetches technical docs with examples for agent use.
API discovery
Finds relevant APIs and returns listings with descriptions.
Deprecated code checks
Reviews code snippets for outdated patterns and returns an analysis report.
URL content extraction
Parses web pages and handles GitHub repository URLs specially.
Persistent chat
Keeps conversation history in local SQLite storage for follow-up questions.
Keyless setup
Uses browser automation instead of API keys, with optional Pro account login.
How to get it
- 1Run
git clone https://github.com/wysh3/perplexity-mcp-zerver.git cd perplexity-mcp-zerver bun install bun run build
- 2Run
bun run build bun run login
README
Perplexity MCP Zerver
A minimalist research server implementing the Model Context Protocol (MCP) to deliver AI-powered research capabilities through Perplexity's web interface.
Research Capabilities
- Intelligent Web Research: Search and summarize content without API limits
- Persistent Conversations: Maintain context with local SQLite chat storage
- Content Extraction: Clean article extraction with GitHub repository parsing
- Developer Tooling: Documentation retrieval, API discovery, code analysis
- Keyless Operation: Browser automation replaces API key requirements
Available Tools
Search (search)
Perform research queries with configurable depth
Returns raw text results
Get Documentation (get_documentation)
Retrieve technical documentation with examples
Returns structured documentation
Find APIs (find_apis)
Discover relevant APIs for development needs
Returns API listings and descriptions
Check Deprecated Code (check_deprecated_code)
Analyze code snippets for outdated patterns
Returns analysis report
Extract URL Content (extract_url_content)
Parse web content with automatic GitHub handling
Returns structured content metadata
Chat (chat_perplexity)
Persistent conversations with context history
Returns conversation state in JSON format
Getting Started
Prerequisites
- Bun runtime
- Node.js 18+ (for TypeScript compilation)
Installation
git clone https://github.com/wysh3/perplexity-mcp-zerver.git
cd perplexity-mcp-zerver
bun install
bun run build
Configuration
Add to your MCP configuration file:
{
"mcpServers": {
"perplexity-server": {
"command": "bun",
"args": ["/absolute/path/to/build/main.js"],
"timeout": 300
}
}
}
Usage
Initiate commands through your MCP client:
- "Use perplexity to research quantum computing advancements"
- "Ask perplexity-server for React 18 documentation"
- "Begin conversation with perplexity about neural networks"
🔐 Pro Account Support (Optional)
Use your Perplexity Pro subscription for access to better models (GPT-5.1, Claude Sonnet 4.5) and higher limits.
One-Time Setup
bun run build
bun run login
A browser window will open. Log in using email (recommended for best compatibility), then close the browser. Your session is now saved!
Note: Google/SSO login may work but email login is more reliable with the browser automation.
Environment Variables
| Variable | Default | Description |
|---|---|---|
PERPLEXITY_BROWSER_DATA_DIR | ~/.perplexity-mcp | Browser profile directory |
PERPLEXITY_PERSISTENT_PROFILE | true | Set to false for anonymous mode |
Technical Comparison
| Feature | This Implementation | Traditional APIs |
|---|---|---|
| Authentication | None required | API keys |
| Cost | Free | Usage-based |
| Data Privacy | Local processing | Remote servers |
| GitHub Integration | Native support | Limited |
| History Persistence | SQLite storage | Session-based |
Troubleshooting
Server Connection Issues
- Verify absolute path in configuration
- Confirm Node.js installation with
node -v - Ensure build completed successfully
Content Extraction
- GitHub paths must use full repository URLs
- Adjust link recursion depth in source configuration
Origins & License
based on - DaInfernalCoder/perplexity-researcher-mcp
refactored from - sm-moshi/docshunter
Licensed under GNU GPL v3.0 - View License
This project interfaces with Perplexity via browser automation. Use responsibly and ethically. Stability depends on Perplexity's website consistency. Educational use only.
Files in the repo
- src
- .editorconfig
- .gitignore
- biome.json
- bun.lock
- LICENSE
- mise.toml
- package.json
- README.md
- tsconfig.json
- vitest.config.ts
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.