The Perplexity API Platform MCP Server provides AI assistants with real-time web search, reasoning, and research capabilities through Perplexity's Sonar models and Search API.
Web Search (perplexity_search): Perform direct web searches returning ranked results with titles, URLs, and snippets. Supports filtering by country (ISO code), limiting results (1–20), and controlling token extraction per page (256–2048 tokens).
Conversational AI with Search (perplexity_ask): Ask general-purpose questions using the sonar-pro model, which combines conversational AI with real-time web search for quick, up-to-date answers.
Deep Research (perplexity_research): Conduct comprehensive research using the sonar-deep-research model, returning detailed reports with citations. Supports an optional strip_thinking parameter to remove internal reasoning tags and save context tokens.
Advanced Reasoning (perplexity_reason): Solve complex analytical problems using the sonar-reasoning-pro model. Also supports the optional strip_thinking parameter.
The server can run locally or be deployed as an HTTP server for cloud/shared environments, with support for proxies, custom API endpoints, timeouts, and configurable log levels.
Provides real-time web search, deep research, and advanced reasoning capabilities through Perplexity's Sonar models and Search API, enabling AI assistants to access current information, conduct comprehensive research, and solve complex analytical problems.
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 API Platform MCP Server research the latest advancements in quantum computing and summarize key breakthroughs"
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.
The official MCP server implementation for the Perplexity API Platform, providing AI assistants with real-time web search, reasoning, and research capabilities through the Agent API and the Search API.
The remote MCP server is hosted by Perplexity and is the easiest way to get started: same tools, nothing to install or update. The Cursor and VS Code buttons at the top of this page connect to it with one click. If your MCP client does not support remote servers yet, skip to the local server setup below. Connect over Streamable HTTP with your Perplexity API key:
https://api.perplexity.ai/mcpFor Claude Code:
claude mcp add --transport http perplexity https://api.perplexity.ai/mcp --header "Authorization: Bearer YOUR_API_KEY"See the MCP integration docs for manual Cursor/VS Code configuration, usage from the Anthropic API, and setup for other clients.
Related MCP server: Perplexity Ask MCP Server
Get your Perplexity API Key from the API Portal
Replace your_key_here in the configurations below with your API key
(Optional) Set timeout: PERPLEXITY_TIMEOUT_MS=600000 (default: 5 minutes)
(Optional) Set custom base URL: PERPLEXITY_BASE_URL=https://your-custom-url.com (default: https://api.perplexity.ai)
(Optional) Set log level: PERPLEXITY_LOG_LEVEL=DEBUG|INFO|WARN|ERROR (default: ERROR)
claude mcp add perplexity --env PERPLEXITY_API_KEY="your_key_here" -- npx -y @perplexity-ai/mcp-serverOr install via plugin:
export PERPLEXITY_API_KEY="your_key_here"
claude
# Then run: /plugin marketplace add perplexityai/modelcontextprotocol
# Then run: /plugin install perplexitycodex mcp add perplexity --env PERPLEXITY_API_KEY="your_key_here" -- npx -y @perplexity-ai/mcp-serverThis repository is packaged as an Agent Plugin, so clients that support the standard can install it directly from this repository. The Agent Plugins format does not carry secrets, so set the PERPLEXITY_API_KEY environment variable through your client's plugin or MCP settings.
Most clients can be configured manually using the same mcpServers wrapper in their client config (as shown for Cursor). If a client has a different schema, check its docs for the exact wrapper format.
For manual setup, these clients all use the same mcpServers structure:
Client | Config File |
Cursor |
|
Claude Desktop |
|
Kiro |
|
Windsurf |
|
VS Code |
|
{
"mcpServers": {
"perplexity": {
"command": "npx",
"args": ["-y", "@perplexity-ai/mcp-server"],
"env": {
"PERPLEXITY_API_KEY": "your_key_here"
}
}
}
}If you are running this server at work—especially behind a company firewall or proxy—you may need to tell the program how to send its internet traffic through your network's proxy. Follow these steps:
1. Get your proxy details
Ask your IT department for your HTTPS proxy address and port.
You may also need a username and password.
2. Set the proxy environment variable
The easiest and most reliable way for Perplexity MCP is to use PERPLEXITY_PROXY. For example:
export PERPLEXITY_PROXY=https://your-proxy-host:8080If your proxy needs a username and password, use:
export PERPLEXITY_PROXY=https://username:password@your-proxy-host:80803. Alternate: Standard environment variables
If you'd rather use the standard variables, we support HTTPS_PROXY and HTTP_PROXY.
The server checks proxy settings in this order:PERPLEXITY_PROXY → HTTPS_PROXY → HTTP_PROXY. If none are set, it connects directly to the internet.
URLs must include https://. Typical ports are 8080, 3128, and 80.
For cloud or shared deployments, run the server in HTTP mode.
Variable | Description | Default |
| Your Perplexity API key | Required |
| Custom base URL for API requests |
|
| HTTP server port |
|
| Network interface to bind to. Defaults to loopback. Set to |
|
| CORS origins (comma-separated). Defaults to empty (no cross-origin browser requests). Set to an explicit allowlist (e.g. | (empty) |
| Additional | (loopback only) |
docker build -t perplexity-mcp-server .
docker run -p 8080:8080 -e PERPLEXITY_API_KEY=your_key_here perplexity-mcp-serverexport PERPLEXITY_API_KEY=your_key_here
npm install && npm run build && npm run start:httpThe server will be accessible at http://localhost:8080/mcp
Direct web search using the Perplexity Search API. Returns ranked search results with metadata, perfect for finding current information. Supports recency filters (search_recency_filter) and domain restrictions (search_domain_filter).
General-purpose conversational AI with real-time web search, backed by the Agent API fast preset. Great for quick questions and everyday searches.
Deep, comprehensive research backed by the Agent API high preset. Ideal for thorough analysis and detailed reports. Runs can take minutes; the server streams the run and reports progress to clients that request it.
Advanced reasoning and problem-solving backed by the Agent API medium preset. Perfect for complex analytical tasks.
Presets are managed configurations (model, search setup, step budget) that Perplexity keeps tuned over time; see thepresets guide. Earlier versions of this server called the legacy sonar-pro, sonar-reasoning-pro, and sonar-deep-research models and accepted strip_thinking / reasoning_effort parameters. Those parameters are no longer part of the tool schemas and are ignored if sent; the Agent API produces no <think> tags.
The package also exports the server factory for embedding in your own Node process:
import { createPerplexityServer } from "@perplexity-ai/mcp-server";
// Single-tenant: reads PERPLEXITY_API_KEY from the environment.
const server = createPerplexityServer("my-service");
// Multi-tenant hosts resolve the key per call instead. When a provider is
// set, the environment variable is never consulted, and a provider that
// returns no key fails the call rather than falling back.
const tenantServer = createPerplexityServer("my-service", {
apiKey: () => currentRequestApiKey,
});Mount the returned server on any MCP transport (stdio, streamable HTTP, in-memory).
API Key Issues: Ensure PERPLEXITY_API_KEY is set correctly
Connection Errors: Check your internet connection and API key validity
Tool Not Found: Make sure the package is installed and the command path is correct
Timeout Errors: For very long research queries, set PERPLEXITY_TIMEOUT_MS to a higher value
Proxy Issues: Verify your PERPLEXITY_PROXY or HTTPS_PROXY setup and ensure api.perplexity.ai isn't blocked by your firewall.
EOF / Initialize Errors: Some strict MCP clients fail because npx writes installation messages to stdout. Use npx -yq instead of npx -y to suppress this output.
For support, visit community.perplexity.ai or file an issue.
Engages in a conversation using the Sonar API. Accepts an array of messages (each with a role and content) and returns a chat completion response from the Perplexity model.
| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes | Array of conversation messages |
| Name | Required | Description |
|---|---|---|
| response | Yes | The response from Perplexity |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=true and openWorldHint=true, which the description doesn't contradict. The description adds that it 'engages in a conversation' and uses the 'Sonar API', providing some context beyond annotations, but lacks details on rate limits, authentication needs, or specific behavioral traits like response format or error handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, consisting of two sentences that directly state the tool's action and parameters without unnecessary details. Every sentence contributes essential information, making it efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a conversational AI tool with one parameter), the description covers the basic purpose and input. With annotations providing safety hints and an output schema presumably detailing the response, the description is reasonably complete, though it could benefit from more behavioral context or sibling differentiation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the single parameter 'messages' fully documented in the schema. The description mentions 'accepts an array of messages (each with a role and content)', which aligns with but doesn't add meaningful semantics beyond the schema, such as usage examples or constraints on message structure.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'engages in a conversation using the Sonar API' and 'returns a chat completion response from the Perplexity model', which specifies the verb (engages/returns) and resource (conversation/response). However, it doesn't explicitly differentiate from sibling tools like perplexity_reason or perplexity_search, which likely have similar conversational purposes but different scopes or behaviors.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings (perplexity_reason, perplexity_research, perplexity_search). It mentions the general action but offers no context about appropriate scenarios, exclusions, or alternatives, leaving the agent to guess based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Performs reasoning tasks using the Perplexity API. Accepts an array of messages (each with a role and content) and returns a well-reasoned response using the sonar-reasoning-pro model.
| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes | Array of conversation messages | |
| strip_thinking | No | If true, removes <think>...</think> tags and their content from the response to save context tokens. Default is false. |
| Name | Required | Description |
|---|---|---|
| response | Yes | The response from Perplexity |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=true and openWorldHint=true, which the description doesn't contradict. The description adds value by specifying the model (sonar-reasoning-pro) and the purpose (reasoning tasks), but it lacks details on behavioral traits like rate limits, error handling, or response format beyond what annotations provide. No contradiction is present.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, consisting of two sentences that efficiently convey the core functionality and model used. Every sentence adds value without redundancy, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (reasoning tasks with an API), annotations cover safety (readOnlyHint) and scope (openWorldHint), and an output schema exists, the description is reasonably complete. It specifies the model and purpose, but could improve by differentiating from siblings or adding more context on use cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents the parameters (messages array and strip_thinking boolean). The description adds no additional meaning beyond what's in the schema, such as examples or usage tips for parameters. Baseline 3 is appropriate as the schema handles the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool 'performs reasoning tasks using the Perplexity API' and 'returns a well-reasoned response using the sonar-reasoning-pro model,' which is a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like perplexity_ask, perplexity_research, or perplexity_search, leaving some ambiguity about when to choose this tool over others for reasoning tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings (perplexity_ask, perplexity_research, perplexity_search). It mentions the model (sonar-reasoning-pro) but doesn't specify use cases, exclusions, or alternatives, leaving the agent without clear context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Performs deep research using the Perplexity API. Accepts an array of messages (each with a role and content) and returns a comprehensive research response with citations.
| Name | Required | Description | Default |
|---|---|---|---|
| messages | Yes | Array of conversation messages | |
| strip_thinking | No | If true, removes <think>...</think> tags and their content from the response to save context tokens. Default is false. |
| Name | Required | Description |
|---|---|---|
| response | Yes | The response from Perplexity |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate read-only and open-world hints, which the description doesn't contradict. It adds value by specifying that it 'returns a comprehensive research response with citations', providing context on output behavior. However, it lacks details on rate limits, authentication needs, or response format beyond citations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core purpose, uses two concise sentences with zero waste, and efficiently conveys key information without redundancy. Every sentence earns its place by adding distinct value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of annotations and an output schema, the description is reasonably complete for a research tool. It covers the basic action and output type, though it could benefit from more context on when to use versus siblings or behavioral traits like response structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents parameters. The description adds minimal semantics by mentioning 'array of messages' and 'comprehensive research response', but doesn't elaborate on parameter usage beyond what's in the schema. Baseline 3 is appropriate given high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Performs deep research') and resource ('using the Perplexity API'), and distinguishes from siblings by specifying 'deep research' rather than generic queries. However, it doesn't explicitly contrast with 'perplexity_reason' or 'perplexity_search' to fully differentiate purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like 'perplexity_ask' or 'perplexity_search'. The description mentions 'deep research' but doesn't clarify scenarios or prerequisites for choosing this over sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Performs web search using the Perplexity Search API. Returns ranked search results with titles, URLs, snippets, and metadata. Perfect for finding up-to-date facts, news, or specific information.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query string | |
| max_results | No | Maximum number of results to return (1-20, default: 10) | |
| max_tokens_per_page | No | Maximum tokens to extract per webpage (default: 1024) | |
| country | No | ISO 3166-1 alpha-2 country code for regional results (e.g., 'US', 'GB') |
| Name | Required | Description |
|---|---|---|
| results | Yes | Formatted search results |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, indicating safe, external data access. The description adds valuable behavioral context beyond this by specifying the return format ('ranked search results with titles, URLs, snippets, and metadata') and the tool's strength for 'up-to-date' information, which helps the agent understand output structure and timeliness without contradicting annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences: the first states the core functionality and output, and the second provides usage context. Every phrase adds value without redundancy, making it front-loaded and appropriately sized for a search tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity, rich annotations (readOnlyHint, openWorldHint), 100% schema coverage, and the presence of an output schema (implied by context signals), the description is complete enough. It covers purpose, output format, and ideal use cases, leaving technical details to structured fields.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing full documentation for all 4 parameters. The description doesn't add any parameter-specific details beyond what the schema already covers, such as explaining how 'country' affects results or typical 'query' formats. This meets the baseline of 3 when schema coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Performs web search') and resource ('using the Perplexity Search API'), and distinguishes it from siblings by emphasizing web search functionality rather than conversational or analytical approaches. The phrase 'Perfect for finding up-to-date facts, news, or specific information' further clarifies its distinct use case.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool ('Perfect for finding up-to-date facts, news, or specific information'), which implicitly suggests it's for factual retrieval rather than reasoning or research tasks handled by siblings. However, it doesn't explicitly name alternatives or state when not to use it, which prevents a perfect score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.6.1perplexity_askperplexity_reasonperplexity_researchperplexity_searchThe tools are mostly distinct with clear primary purposes: 'ask' for general conversation, 'reason' for reasoning tasks, 'research' for deep research with citations, and 'search' for web search results. However, 'ask' and 'reason' could be confused as both involve chat completions with similar inputs, potentially leading to misselection in ambiguous scenarios.
All tool names follow a consistent 'perplexity_' prefix with descriptive suffixes (ask, reason, research, search), using snake_case uniformly. This predictable pattern makes it easy for an agent to understand and navigate the tool set without confusion.
With 4 tools, the count is well-scoped for a server focused on interacting with the Perplexity API. Each tool serves a distinct function (conversation, reasoning, research, search), and there are no redundant or unnecessary tools, making the set efficient and appropriate for the domain.
The tool set covers core functionalities of the Perplexity API, including general chat, reasoning, research, and web search, which aligns well with the server's purpose. A minor gap is the lack of tools for managing conversations (e.g., clearing history or handling follow-ups), but agents can work around this using the provided message arrays.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Enable AI assistants to perform web searches using Perplexity's Sonar Pro.
Real-time web search, reasoning, and research through Perplexity's API
Give AI assistants access to real-time data. Search the web, compare flights, find hotels, and more.
Agent-native search engine with live web research optimized for AI agents.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/perplexityai/modelcontextprotocol'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
