MewCP Perplexity MCP

Answer any question with live web search, citations, and AI reasoning — all in one call.

A Model Context Protocol (MCP) server that exposes Perplexity AI's API for real-time web search and conversational queries with cited sources.

The Perplexity MCP Server provides AI-powered web search with grounded, citation-backed responses:

- Query the live web and get LLM-synthesized answers with source references
- Control response length, temperature, and the underlying search model
- Browse available Perplexity models to choose the right capability for each task

- Giving AI assistants access to current events, news, and real-time information
- Answering research questions that require up-to-date facts beyond the model's training cutoff
- Enriching AI workflows with cited, verifiable web sources

Returns a status object confirming the server is running and reachable.

{ "status": "ok", "server": "CL Perplexity MCP Server" }

Sends a query to Perplexity's online search models and returns an LLM-generated answer with citations from live web sources.

- query (string, required) — Search query to look up on the web - model (string, optional) — Model to use (default: llama-3.1-sonar-small-128k-online) - max_tokens (integer, optional) — Maximum tokens in the response, 1–4096 - temperature (float, optional) — Sampling temperature 0–2; higher = more creative (default: model default)

{ "success": true, "query": "latest AI research papers 2025", "response": "Recent AI research has focused on...", "model": "llama-3.1-sonar-small-128k-online", "usage": { "prompt_tokens": 12, "completion_tokens": 320, "total_tokens": 332 } }

Returns all models available through the Perplexity API, grouped into online (web search) and offline (non-search) categories.

{ "success": true, "total_models": 6, "online_models": [ "llama-3.1-sonar-small-128k-online", "llama-3.1-sonar-large-128k-online", "llama-3.1-sonar-huge-128k-online" ], "other_models": [ "llama-3.1-sonar-small-128k-chat", "llama-3.1-sonar-large-128k-chat" ], "all_models": [...] }

Online models(include live web search):

- llama-3.1-sonar-small-128k-online— Fast, cost-efficient; default for web search
- llama-3.1-sonar-large-128k-online— Higher quality answers, more thorough search
- llama-3.1-sonar-huge-128k-online— Best quality, most comprehensive; highest cost

Useget_modelsto retrieve the current full list — new models are added periodically.

- temperature— Controls randomness;0.0for focused factual answers,1.0+for creative responses (range: 0–2)
- max_tokens— Caps response length; useful for controlling cost and latency (range: 1–4096)

Perplexity API usage is billed per request based on the model and token count. Online models consume additional credits for web search.

- Cause:API key not provided in request headers or incorrect format
- Solution:
- VerifyAuthorization: Bearer YOUR_API_KEYandX-Mewcp-Credential-Id: CREDENTIAL-IDheaders are present
- Check API key is active in your MewCP account

- Cause:API calls have exceeded your request limits
- Solution:
- Check credit usage in your Curious Layer dashboard
- Upgrade to a paid plan or add credits for higher limits
- Contact support for credit adjustments

- Cause:No Perplexity credential linked to your account
- Solution:
- Go toCredentialsin your MewCP dashboard
- Add your Perplexity API key
- Retry the request with the correctX-Mewcp-Credential-Idheader

- Cause:JSON payload is invalid or missing required fields
- Solution:
- Validate JSON syntax before sending
- Ensure thequeryparameter is included and is a non-empty string
- Check thattemperatureis between 0.0 and 2.0 andmax_tokensis between 1 and 4096

- Cause:Incorrect server name in the API endpoint
- Solution:
- Verify endpoint format:{server-name}/mcp/{tool-name}
- Use correct server name from documentation
- Check available servers in your Curious Layer account

- Cause:Upstream Perplexity API returned an error
- Solution:
- Check Perplexity service status atPerplexity Status Page
- Verify your API key has sufficient credits for the selected model
- Review the error message for specific details (e.g. rate limit exceeded, invalid model ID)

- Perplexity API Documentation— Official API reference
- Perplexity Model Cards— Model capabilities and pricing
- FastMCP Docs— FastMCP specification
- FastMCP Credentials— FastMCP Credentials package for credential handling

Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance