Perplexity MCP Server
Provides tools to perform web searches and deep research using Perplexity's Sonar models, returning answers with citations and search results.
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 Serversummarize the latest space exploration news"
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
Python MCP server that exposes Perplexity Sonar Chat Completions to any MCP client (Cursor, Claude Desktop, custom agents).
Tools
Tool | Default model | Purpose |
|
| General web search |
|
| Comprehensive synthesis |
Both tools accept optional Sonar parameters and return JSON:
{
"answer": "...",
"citations": ["https://..."],
"search_results": [],
"model": "sonar-pro",
"usage": {}
}Optional parameters
Parameter | Values / format | When to use |
|
| Lower = more focused; raise only for more varied phrasing |
|
| Cap answer length; omit for API default |
|
| News / “latest” questions; omit for evergreen topics |
|
| Absolute start of publication window |
|
| Absolute end of publication window |
| up to 20 domains; allowlist or | Trusted sources only, or exclude noisy sites |
|
| Papers ( |
|
| Override tool default only when you need a different speed/depth tradeoff |
Prefer date filters over search_recency_filter when the window is known exactly. Queries are capped at 4,000 characters. The API key is never logged or returned in tool output.
Related MCP server: Perplexity Web-Search MCP
Setup
Copy env template and add your Perplexity API key:
cp .env.example .envInstall with uv:
uv syncRun locally (stdio)
uv run mcp-perplexityCursor / Claude Desktop
Add to your MCP config (adjust the project path):
{
"mcpServers": {
"perplexity": {
"command": "uv",
"args": ["--directory", "C:/Users/KozakJ/git/mcp_perplexity", "run", "mcp-perplexity"],
"env": {
"PERPLEXITY_API_KEY": "pplx-your-api-key-here"
}
}
}
}Or rely on a .env file in the project directory (PERPLEXITY_API_KEY=...).
Cursor / Claude Desktop (container, stdio)
Rebuild after image changes, then only the API key is required — other settings use the same defaults as local runs:
{
"mcpServers": {
"perplexity": {
"command": "podman",
"args": [
"run", "-i", "--rm",
"-e", "PERPLEXITY_API_KEY",
"mcp-perplexity"
],
"env": {
"PERPLEXITY_API_KEY": "pplx-your-api-key-here"
}
}
}
}Override any setting the same way (-e MCP_PORT, etc.) only when you need non-defaults.
Run with Podman (streamable HTTP)
podman compose needs a compose provider (podman-compose or Docker Compose). On a plain Podman install, use build + run:
podman build -t mcp-perplexity .
podman run --rm -p 8000:8000 --env-file .env ^
-e MCP_TRANSPORT=streamable-http ^
-e MCP_HOST=0.0.0.0 ^
-e MCP_PORT=8000 ^
--name mcp-perplexity mcp-perplexity(On bash/zsh, replace ^ with \.)
If you have a compose provider installed (pip install podman-compose, or Docker Compose):
podman compose up --buildEndpoint: http://localhost:8000/mcp (Streamable HTTP). Bind to trusted networks only — this image does not add HTTP auth.
Configuration
Variable | Default | Description |
| (required) | Perplexity API key |
|
|
|
|
| HTTP bind host |
|
| HTTP bind port |
|
| Soft client-side requests/minute limit |
|
| Max concurrent API calls |
|
| Search timeout (seconds) |
|
| Deep research timeout (seconds) |
|
| Retries on 429/5xx and transport errors |
Retries use exponential backoff (honors Retry-After when present). Logging goes to stderr only so stdio JSON-RPC stays clean.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceIntegrates the Sonar API to provide Claude with real-time web-wide research capabilities. Enables conversational web searches through Perplexity's AI-powered search engine for up-to-date information retrieval.Last updated1,243MIT
- FlicenseBqualityDmaintenanceEnables AI assistants to perform real-time web and academic searches using Perplexity's Sonar API.Last updated2
- AlicenseBqualityDmaintenanceEnables web search using Perplexity AI's API, allowing users to search the web with optional recency filters and integration with Claude, Cursor, and other MCP clients.Last updated1MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to perform web searches and retrieve real-time information using Perplexity AI's Sonar models, with support for multiple search modes and easy integration with MCP clients.Last updated51MIT
Related MCP Connectors
Serper MCP — wraps the Serper Google Search API (serper.dev)
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
The best web search for your AI Agent
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jujubytes-a11y/mcp_perplexity'
If you have feedback or need assistance with the MCP directory API, please join our Discord server