Exposes Perplexity AI's search capabilities, enabling web searching and planned integration with Perplexity Spaces for thread summarization and multi-source data synthesis.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Perplexity MCP Serversearch for the latest news on SpaceX's Starship launch"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Perplexity MCP Server
MCP server that exposes Perplexity AI's search capabilities to Claude.
🚧 Development Status
Current Version: v0.1.0-alpha (In Active Development)
✅ Completed (Phase 1)
Project foundation and security setup
.gitignore with comprehensive exclusions
.env.example template with placeholder API key
requirements.txt with pinned dependencies
SECURITY.md with security policy
README.md with initial structure
Apache 2.0 License
🚧 In Progress (Phase 2-6)
Configuration management (config.py)
Perplexity API client (perplexity_client.py)
MCP server implementation (server.py)
Testing and validation
Documentation finalization
🔮 Planned (Future Phases)
Perplexity Spaces integration
Memory and context management
Thread summarization across Spaces
Cross-platform data synthesis
Document generation from multi-source data
Note: This project is in early development. The API and features may change.
Setup
Clone the repository
Copy
.env.exampleto.envAdd your Perplexity API key to
.envInstall dependencies:
pip install -r requirements.txtRun the server:
python server.py
Configuration
See .env.example for configuration options.
Security
See SECURITY.md for security policies and best practices.
Usage
[To be added after implementation]
Troubleshooting
[To be added after implementation]