Perplexity Search
About
Integrates with Perplexity AI search API to enable real-time web searches with customizable parameters for recency filtering, domain-specific queries, and citation support.
Details
- Author
- chenxilol
- Repository
- chenxilol/perplexity-mcp-go
- GitHub stars
- 4
- License
- MIT License
- Categories
- Search, Other, AI, Design, Developer Tools, Frontend, Infrastructure, Knowledge Base
- Tags
- #web
Jump to
- perplexity_search: Perform web searches and return results, including citations
- Parameters:
- query (string, required): The search query
- search_recency_filter (string, optional): Filter results by time (month, week, day, hour)
- max_tokens (integer, optional): Maximum number of tokens to return
- temperature (number, optional, default: 0.2): Controls randomness in response
- top_p (number, optional, default: 0.9): Nucleus sampling threshold
- search_domain_filter (array, optional): List of domains to limit search results
- return_images (boolean, optional): Include image links in results
- return_related_questions (boolean, optional): Include related questions
- top_k (number, optional, default: 0): Number of tokens for top-k filtering
- stream (boolean, optional): Stream response incrementally
- presence_penalty (number, optional, default: 0): Adjust likelihood of new topics
- frequency_penalty (number, optional, default: 1): Reduce repetition
- web_search_options (object, optional): Configuration options for web search
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Perplexity SearchCommand (node, npx, python, etc.)/path/to/perplexity-search-mcpEnvironment-
PERPLEXITY_API_KEY
your-api-key-here
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
PERPLEXITY_API_KEY
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
1. Clone the repository:
git clone https://github.com/chenxilol/perplexity-mcp-go.git
cd perplexity-mcp-go
2. Build the application:
go build -o perplexity-search-mcp
To install Perplexity Search Golang for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @chenxilol/perplexity-mcp-go --client claude
1. Set your Perplexity API key:
export PERPLEXITY_API_KEY="your-api-key-here"
2. Run the server:
./perplexity-search-mcp
Once configured, Claude can use the perplexity_search tool via MCP to perform real-time web searches.
Example search with parameters:
{
"query": "latest AI research developments",
"search_recency_filter": "week",
"temperature": 0.5,
"return_related_questions": true,
"web_search_options": {
"search_context_size": "high"
}
}
perplexity_search
Perform web searches and return results, including citations. Parameters: query (string, required), search_recency_filter (string, optional), max_tokens (integer, optional), temperature (number, optional, default: 0.2), top_p (number, optional, default: 0.9), search_domain_filter (array, optional), return_images (boolean, optional), return_related_questions (boolean, optional), top_k (number, optional, default: 0), stream (boolean, optional), presence_penalty (number, optional, default: 0), frequency_penalty (number, optional, default: 1), web_search_options (object, optional).
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"perplexity search": {
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here"
},
"args": [],
"command": "/path/to/perplexity-search-mcp"
}
}
}
Linux
{
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here"
},
"args": [],
"command": "/path/to/perplexity-search-mcp"
}
Macos
{
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here"
},
"args": [],
"command": "/path/to/perplexity-search-mcp"
}
Windows
{
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here"
},
"args": [],
"command": "/path/to/perplexity-search-mcp"
}
Perplexity Search MCP Server
A Go implementation of a Perplexity Search MCP server that allows large language models (LLMs) to access the Perplexity search API through the Model Context Protocol (MCP).
Features
- perplexity_search: Perform web searches and return results, including citations
- Parameters:
- query (string, required): The search query
- search_recency_filter (string, optional): Filter results by time (month, week, day, hour)
- max_tokens (integer, optional): Maximum number of tokens to return
- temperature (number, optional, default: 0.2): Controls randomness in response
- top_p (number, optional, default: 0.9): Nucleus sampling threshold
- search_domain_filter (array, optional): List of domains to limit search results
- return_images (boolean, optional): Include image links in results
- return_related_questions (boolean, optional): Include related questions
- top_k (number, optional, default: 0): Number of tokens for top-k filtering
- stream (boolean, optional): Stream response incrementally
- presence_penalty (number, optional, default: 0): Adjust likelihood of new topics
- frequency_penalty (number, optional, default: 1): Reduce repetition
- web_search_options (object, optional): Configuration options for web search
Setup & Usage
Installing via Smithery
To install Perplexity Search Golang for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @chenxilol/perplexity-mcp-go --client claude
Prerequisites
- Go 1.23 or higher
- Perplexity API key
Installation
1. Clone the repository:
git clone https://github.com/chenxilol/perplexity-mcp-go.git
cd perplexity-mcp-go
2. Build the application:
go build -o perplexity-search-mcp
Running Locally
1. Set your Perplexity API key:
export PERPLEXITY_API_KEY="your-api-key-here"
2. Run the server:
./perplexity-search-mcp
Integrating with Claude
1. Copy the provided claude_desktop_config.json to your Claude configuration directory:
- Windows: %USERPROFILE%\AppData\Roaming\Claude\claude_desktop_config.json
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json
2. Edit the configuration file to include your API key:
{
"mcpServers": {
"perplexity-search": {
"command": "/path/to/perplexity-search-mcp",
"env": {
"PERPLEXITY_API_KEY": "your-api-key-here"
}
}
}
}
Docker Support
1. Build the Docker image:
docker build -t perplexity-search-mcp:latest .
2. Run the container:
docker run -i --rm -e PERPLEXITY_API_KEY=your-api-key-here perplexity-search-mcp:latest
Example Usage
Once configured, Claude can use the perplexity_search tool via MCP to perform real-time web searches.
Example search with parameters:
{
"query": "latest AI research developments",
"search_recency_filter": "week",
"temperature": 0.5,
"return_related_questions": true,
"web_search_options": {
"search_context_size": "high"
}
}
Troubleshooting
If you encounter issues:
1. Verify your API key is correctly set
2. Check network connectivity
3. Examine stderr logs for error messages
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Model Context Protocol for the MCP specification
- MCP-Go for the Go MCP implementation
- Perplexity for their search API
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




