Skip to main content
Glama
enesjakozh
jsonallen

Perplexity MCP Server

by jsonallen
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Remote

perplexity-mcp MCP server

A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API. Works with the Anthropic Claude desktop client.

Example

Let's you use prompts like, "Search the web to find out what's new at Anthropic in the past week."

Related MCP server: Perplexity MCP Server

Glama Scores

Components

Prompts

The server provides a single prompt:

  • perplexity_search_web: Search the web using Perplexity AI

    • Required "query" argument for the search query

    • Optional "recency" argument to filter results by time period:

      • 'day': last 24 hours

      • 'week': last 7 days

      • 'month': last 30 days (default)

      • 'year': last 365 days

    • Uses Perplexity's API to perform web searches

Tools

The server implements one tool:

  • perplexity_search_web: Search the web using Perplexity AI

    • Takes "query" as a required string argument

    • Optional "recency" parameter to filter results (day/week/month/year)

    • Returns search results from Perplexity's API

Installation

Installing via Smithery

To install Perplexity MCP for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install perplexity-mcp --client claude

Requires UV (Fast Python package and project manager)

If uv isn't installed.

# Using Homebrew on macOS
brew install uv

or

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Environment Variables

The following environment variable is required in your claude_desktop_config.json. You can obtain an API key from Perplexity

  • PERPLEXITY_API_KEY: Your Perplexity AI API key

Optional environment variables:

  • PERPLEXITY_MODEL: The Perplexity model to use (defaults to "sonar" if not specified)

    Available models:

    • sonar-deep-research: 128k context - Enhanced research capabilities

    • sonar-reasoning-pro: 128k context - Advanced reasoning with professional focus

    • sonar-reasoning: 128k context - Enhanced reasoning capabilities

    • sonar-pro: 200k context - Professional grade model

    • sonar: 128k context - Default model

    • r1-1776: 128k context - Alternative architecture

And updated list of models is avaiable (here)[https://docs.perplexity.ai/guides/model-cards]

Cursor & Claude Desktop Installation

Add this tool as a mcp server by editing the Cursor/Claude config file.

  "perplexity-mcp": {
    "env": {
      "PERPLEXITY_API_KEY": "XXXXXXXXXXXXXXXXXXXX",
      "PERPLEXITY_MODEL": "sonar"
    },
    "command": "uvx",
    "args": [
      "perplexity-mcp"
    ]
  }

Cursor

  • On MacOS: /Users/your-username/.cursor/mcp.json

  • On Windows: C:\Users\your-username\.cursor\mcp.json

If everything is working correctly, you should now be able to call the tool from Cursor.

Claude Desktop

  • On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

  • On Windows: %APPDATA%/Claude/claude_desktop_config.json

To verify the server is working. Open the Claude client and use a prompt like "search the web for news about openai in the past week". You should see an alert box open to confirm tool usage. Click "Allow for this chat".

Available Tools

1 tool
perplexity_search_webC

Search the web using Perplexity AI with recency filtering

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
recencyNomonth

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description bears full responsibility for behavioral disclosure. It does not mention whether the operation is read-only, any rate limits, authentication requirements, or side effects. The tool is likely a safe read operation but this is not confirmed, leaving the agent without critical behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that efficiently conveys the core purpose. No redundant information is present. However, it could be slightly expanded to include more context without losing conciseness, hence a 4 rather than 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, no annotations, and two parameters with no schema descriptions, the description is severely lacking. It does not specify what the search returns (type of content, structure), any usage limits, or prerequisites. An agent cannot reliably determine if this tool is appropriate for a given task without additional external knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, meaning the schema provides no parameter descriptions. The description adds only 'with recency filtering' which hints at the recency parameter but does not explain the query parameter or the meaning of recency enum values (day, week, month, year). This is insufficient for an agent to form correct parameter values without additional knowledge.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('search'), the resource ('web'), the specific service ('Perplexity AI'), and includes a key feature ('recency filtering'). This is specific and unambiguous, avoiding tautology by adding value beyond the tool name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 or when to consider alternatives. Since there are no sibling tools, the lack of usage context is less critical, but the description could still mention typical use cases (e.g., 'for up-to-date web results with time constraints'). Currently, it merely rephrases the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedperplexity_search_web
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a single, clear purpose that cannot be confused with any other tool in the set.

Naming Consistency5/5

The single tool name follows a consistent verb_noun pattern (perplexity_search_web), and with only one tool, there is no inconsistency to evaluate. The naming is clear and descriptive.

Tool Count2/5

One tool is too few for a server with a broad purpose like web search, as it lacks related operations such as filtering results, getting details, or handling different search types. This minimal set may limit agent functionality in practical scenarios.

Completeness2/5

The server is severely incomplete for web search functionality, offering only a basic search tool without capabilities like refining queries, paginating results, or accessing cached or specific types of content. This creates significant gaps for agents trying to perform comprehensive web searches.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Perplexity MCP Server

    spragginsdesigns
    A
    license
    B
    quality
    D
    maintenance
    This server allows users to perform web searches using Perplexity AI, providing a tool for retrieving search results through a simple API interface.
    1
    112
    3
    Apache 2.0

  • Perplexity MCP Server

    jaacob
    A
    license
    B
    quality
    D
    maintenance
    Facilitates web search capabilities using Perplexity's API, allowing users to retrieve search results through Claude's interface.
    1
    8
    MIT

  • Perplexity MCP Server

    RossH121
    A
    license
    A
    quality
    D
    maintenance
    An MCP server that enables Claude to perform web searches using Perplexity's API with intelligent model selection based on query intent and support for domain and recency filtering.
    6
    4
    MIT

  • MCP Web Research Server

    jevy
    A
    license
    B
    quality
    D
    maintenance
    A server that integrates with Claude Desktop to enable real-time web research capabilities, allowing users to search Google, extract webpage content, and capture screenshots directly from conversations.
    3
    1,202
    MIT

Appeared in Searches