Perplexity API MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PROXY | No | Standard HTTP proxy environment variable. | |
| HTTPS_PROXY | No | Standard HTTPS proxy environment variable. | |
| PERPLEXITY_PROXY | No | Proxy URL (e.g., https://your-proxy-host:8080). Overrides HTTPS_PROXY and HTTP_PROXY. | |
| PERPLEXITY_API_KEY | Yes | Your Perplexity API key | |
| PERPLEXITY_BASE_URL | No | Custom base URL for API requests (default: https://api.perplexity.ai) | https://api.perplexity.ai |
| PERPLEXITY_LOG_LEVEL | No | Log level: DEBUG, INFO, WARN, ERROR (default: ERROR) | ERROR |
| PERPLEXITY_TIMEOUT_MS | No | Timeout in milliseconds (default: 300000) | 300000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| perplexity_askA | Answer a question using web-grounded AI (Sonar Pro model). Best for: quick factual questions, summaries, explanations, and general Q&A. Returns a text response with numbered citations. Fastest and cheapest option. Supports filtering by recency (hour/day/week/month/year), domain restrictions, and search context size. For in-depth multi-source research, use perplexity_research instead. For step-by-step reasoning and analysis, use perplexity_reason instead. |
| perplexity_researchA | Conduct deep, multi-source research on a topic (Sonar Deep Research model). Best for: literature reviews, comprehensive overviews, investigative queries needing many sources. Returns a detailed response with numbered citations. Significantly slower than other tools (30+ seconds). For quick factual questions, use perplexity_ask instead. For logical analysis and reasoning, use perplexity_reason instead. |
| perplexity_reasonA | Analyze a question using step-by-step reasoning with web grounding (Sonar Reasoning Pro model). Best for: math, logic, comparisons, complex arguments, and tasks requiring chain-of-thought. Returns a reasoned response with numbered citations. Supports filtering by recency (hour/day/week/month/year), domain restrictions, and search context size. For quick factual questions, use perplexity_ask instead. For comprehensive multi-source research, use perplexity_research instead. |
| perplexity_searchA | Search the web and return a ranked list of results with titles, URLs, snippets, and dates. Best for: finding specific URLs, checking recent news, verifying facts, discovering sources. Returns formatted results (title, URL, snippet, date) — no AI synthesis. For AI-generated answers with citations, use perplexity_ask instead. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly delineated purpose (quick Q&A, step-by-step reasoning, deep research, raw search) and descriptions explicitly guide which tool to use for which scenario, eliminating ambiguity.
All tools follow a consistent 'perplexity_verb' pattern in snake_case (ask, reason, research, search), making the naming predictable and easy for agents to infer functionality.
Four tools is well-scoped for a search/QA server: covering quick answers, reasoning, deep research, and raw web search without redundancy or missing core functionality.
The tool set covers the primary workflows (factual Q&A, reasoning, multi-source research, raw search) with no major gaps; a potential minor addition could be a batch or follow-up tool, but not essential.