Perplexity

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

Inputs:

- `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)

output:

{
  "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.

Inputs: (none)

Output:

{
  "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

Use get_models to retrieve the current full list — new models are added periodically.

• temperature — Controls randomness; 0.0 for 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)

1. Go to the Perplexity API Settings
2. Sign in or create a Perplexity account
3. Under API Keys, click + Generate
4. Copy the generated key — store it securely, it will not be shown again

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:
  1. Verify Authorization: Bearer YOUR_API_KEY and X-Mewcp-Credential-Id: CREDENTIAL-ID headers are present
  2. Check API key is active in your MewCP account

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

• Cause: No Perplexity credential linked to your account
• Solution:
  1. Go to Credentials in your MewCP dashboard
  2. Add your Perplexity API key
  3. Retry the request with the correct X-Mewcp-Credential-Id header

• Cause: JSON payload is invalid or missing required fields
• Solution:
  1. Validate JSON syntax before sending
  2. Ensure the query parameter is included and is a non-empty string
  3. Check that temperature is between 0.0 and 2.0 and max_tokens is between 1 and 4096

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

• Cause: Upstream Perplexity API returned an error
• Solution:
  1. Check Perplexity service status at Perplexity Status Page
  2. Verify your API key has sufficient credits for the selected model
  3. 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