perplexity_chatLABSCO SUMMARY
Two tools, and the difference matters.
Use the simple ask for a lookup and the chat tool when the follow-up depends on what was said before — passing the message history is what keeps a multi-turn research thread coherent. Model choice is per call, so a cheap small model can handle routine lookups while the large one is reserved for the hard questions.
What it is
A small Node.js bridge between an MCP client and the Perplexity API. It exists so a model that cannot search can hand the question to one that can, and get back an answer grounded in current web results.
What you get
perplexity_ask— send onequeryand get the answer back, with an optionalmodelperplexity_chat— a full chat completion:messagesas an array of role and content objects, plus optionalmodeland atemperaturebetween 0 and 2- A choice of three online models on either tool:
llama-3.1-sonar-small-128k-online,llama-3.1-sonar-large-128k-online,llama-3.1-sonar-huge-128k-online
Requirements
A Perplexity API key, set as PERPLEXITY_API_KEY in the client's env block. There is no published binary: clone the repository, npm install, npm run build, then point the config at node path/to/perplexity-mcp-server/dist/index.js. Communicates over stdio. Package perplexity-mcp-server at 1.0.0, ISC licensed.
Setup effort
Build from source — git clone https://github.com/laodev1/perplexity-mcp-server.git
USE CASES
01
Checking a fact the model's training data predates
Send the question straight through and get an answer from an online model instead of a confident guess.
02
Researching across several follow-up questions
Pass the accumulated messages so each answer builds on the last rather than starting cold.
03
Trading cost against depth
Name the small online model for routine lookups and the huge one when the answer needs to be thorough.
2 tools
Listed in project docs. Your client may show a different list.
perplexity_askBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- Node.js and npm
- PERPLEXITY_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
TERMINAL
git clone https://github.com/laodev1/perplexity-mcp-server.git
cd perplexity-mcp-server
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"perplexity": {
"command": "node",
"args": [
"<YOUR_PATH_TO_PERPLEXITY_MCP_SERVER>\\dist\\index.js"
],
"env": {
"PERPLEXITY_API_KEY": "<YOUR_PERPLEXITY_API_KEY>"
}
}
}
}<YOUR_PATH_TO_PERPLEXITY_MCP_SERVER> is the full path of your clone, so the path ends in dist\index.js (use forward slashes on macOS and Linux). Restart Claude Desktop afterwards.
