A Model Context Protocol (MCP) server that provides search functionality using Perplexica's AI-powered search engine.
Perplexica MCP Server is an MCP project maintained in the thetom42/perplexica-mcp repository. The maintainer describes its purpose as “A Model Context Protocol (MCP) server that provides search functionality using Perplexica's AI-powered search engine”. Read the project documentation for the complete scope.
The documented pypi package is perplexica-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares PERPLEXICA_BACKEND_URL, PERPLEXICA_CHAT_MODEL_PROVIDER, PERPLEXICA_CHAT_MODEL_NAME, PERPLEXICA_EMBEDDING_MODEL_PROVIDER, PERPLEXICA_EMBEDDING_MODEL_NAME. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| query | string, required): Search query |
| sources | array, required): Search sources to use. Valid values: "web", "academic", "discussions". Can combine multiple sources. |
| chat_model | object, optional): Chat model configuration |
| embedding_model | object, optional): Embedding model configuration |
| optimization_mode | string, optional): "speed", "balanced", or "quality" |
| history | array, optional): Conversation history as [["human", "text"], ["assistant", "text"]] pairs |
| system_instructions | string, optional): Custom instructions |
| stream | boolean, optional): Whether to stream responses |
{
"mcpServers": {
"perplexica": {
"command": "uvx",
"args": [
"perplexica-mcp",
"stdio"
],
"env": {
"PERPLEXICA_BACKEND_URL": "http://localhost:3000/api/search",
"PERPLEXICA_CHAT_MODEL_PROVIDER": "openai",
"PERPLEXICA_CHAT_MODEL_NAME": "gpt-4o-mini",
"PERPLEXICA_EMBEDDING_MODEL_PROVIDER": "openai",
"PERPLEXICA_EMBEDDING_MODEL_NAME": "text-embedding-3-small"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| PERPLEXICA_BACKEND_URL | Declared in the maintainer’s client configuration. | Check documentation |
| PERPLEXICA_CHAT_MODEL_PROVIDER | Declared in the maintainer’s client configuration. | Check documentation |
| PERPLEXICA_CHAT_MODEL_NAME | Declared in the maintainer’s client configuration. | Check documentation |
| PERPLEXICA_EMBEDDING_MODEL_PROVIDER | Declared in the maintainer’s client configuration. | Check documentation |
| PERPLEXICA_EMBEDDING_MODEL_NAME | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
EU-native web scraping for AI agents. scrape pages, map sites, run background jobs, check usage.
Procure, compare, quote, budget, and execute web extraction or scraping across providers for agents
An MCP server leveraging the Brave Search API for web and local search, with optional HTTP proxy configuration.
Quran Search Engine MCP for AI tools. Provides Quran search, Arabic normalization, and highlighting.