MCP server for Perplexica AI-powered search engine
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"perplexica": {
"env": {
"PERPLEXICA_BASE_URL": "http://localhost:3000",
"PERPLEXICA_CUSTOM_OPENAI_KEY": "your_api_key",
"PERPLEXICA_OPTIMIZATION_MODE": "balanced",
"PERPLEXICA_DEFAULT_CHAT_MODEL": "gpt-4.1",
"PERPLEXICA_DEFAULT_CHAT_PROVIDER": "custom_openai",
"PERPLEXICA_CUSTOM_OPENAI_BASE_URL": "https://api.poe.com/v1",
"PERPLEXICA_DEFAULT_EMBEDDING_MODEL": "xenova-bge-small-en-v1.5",
"PERPLEXICA_DEFAULT_EMBEDDING_PROVIDER": "transformers"
},
"args": [
"-m",
"perplexica_mcp_server.server"
],
"command": "python",
"timeout": 60,
"transport": "stdio"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Language: English | 中文
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in search / ai-ml
Dynamic problem-solving through sequential thought chains
Persistent memory using a knowledge graph
Web and local search using Brave Search API
Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.
MCP Security Weekly
Get CVE alerts and security updates for Perplexica Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
A Model Context Protocol (MCP) server that provides access to Perplexica's AI-powered search engine capabilities.
pip install -r requirements.txt
pip install .
or
uv tool install .
Configure the server to cline:
{
"mcpServers": {
"perplexica": {
"command": "python",
"args": [
"-m", "perplexica_mcp_server.server"
],
"env": {
"PERPLEXICA_DEFAULT_CHAT_PROVIDER":"custom_openai",
"PERPLEXICA_DEFAULT_CHAT_MODEL":"gpt-4.1",
"PERPLEXICA_CUSTOM_OPENAI_BASE_URL":"https://api.poe.com/v1",
"PERPLEXICA_CUSTOM_OPENAI_KEY":"your_api_key",
"PERPLEXICA_DEFAULT_EMBEDDING_PROVIDER":"transformers",
"PERPLEXICA_DEFAULT_EMBEDDING_MODEL":"xenova-bge-small-en-v1.5",
"PERPLEXICA_OPTIMIZATION_MODE":"balanced",
"PERPLEXICA_BASE_URL":"http://localhost:3000"
},
"timeout": 60,
"transport": "stdio"
}
}
}
or
{
"mcpServers": {
"perplexica": {
"command": "uvx",
"args": [
"perplexica-mcp-server"
],
"env": {
"PERPLEXICA_DEFAULT_CHAT_PROVIDER":"custom_openai",
"PERPLEXICA_DEFAULT_CHAT_MODEL":"gpt-4.1",
"PERPLEXICA_CUSTOM_OPENAI_BASE_URL":"https://api.poe.com/v1",
"PERPLEXICA_CUSTOM_OPENAI_KEY":"your_api_key",
"PERPLEXICA_DEFAULT_EMBEDDING_PROVIDER":"transformers",
"PERPLEXICA_DEFAULT_EMBEDDING_MODEL":"xenova-bge-small-en-v1.5",
"PERPLEXICA_OPTIMIZATION_MODE":"balanced",
"PERPLEXICA_BASE_URL":"http://localhost:3000"
},
"timeout": 60,
"transport": "stdio"
}
}
}
Copy env.example to .env and modify as needed:
cp env.example .env
# Edit .env file to set your configuration
Run the MCP server with stdio transport:
python -m perplexica_mcp_server.server
Test the server functionality:
python test/test_client.py
Run test for you perplexica:
python test/test_official_api.py
Supports two output formats:
json: Raw JSON data (default)formatted: Human-readable formatted textMIT License