Skip to main content
Glama
enesjakozh
tanigami

Perplexity MCP Server

by tanigami
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Perplexity MCP Server

MCP Server for the Perplexity API.

:warning: Limitations:

  • The Claude Desktop client may timeout if Perplexity processing takes too long

  • This issue might be resolved if Claude Desktop implements support for long running operations and progress reporting in the future

  • Implementation updates to handle these features will be made if they become available

Components

Tools

  • ask_perplexity: Request chat completion with citations from Perplexity

Related MCP server: Perplexity Insight MCP Server

Quickstart

Install

Claude Desktop

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

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

"mcpServers": {
  "Perplexity": {
    "command": "uvx",
    "args": [
      "mcp-server-perplexity"
    ],
    "env": {
      "PERPLEXITY_API_KEY": "your-perplexity-api-key"
    }
  }
}

Available Tools

1 tool
ask_perplexityA

Perplexity equips agents with a specialized tool for efficiently gathering source-backed information from the internet, ideal for scenarios requiring research, fact-checking, or contextual data to inform decisions and responses. Each response includes citations, which provide transparent references to the sources used for the generated answer, and choices, which contain the model's suggested responses, enabling users to access reliable information and diverse perspectives. This function may encounter timeout errors due to long processing times, but retrying the operation can lead to successful completion. [Response structure]

  • id: An ID generated uniquely for each response.

  • model: The model used to generate the response.

  • object: The object type, which always equals chat.completion.

  • created: The Unix timestamp (in seconds) of when the completion was created.

  • citations[]: Citations for the generated answer.

  • choices[]: The list of completion choices the model generated for the input prompt.

  • usage: Usage statistics for the completion request.

ParametersJSON Schema
NameRequiredDescriptionDefault
modelYesThe name of the model that will complete your prompt.
messagesYesA list of messages comprising the conversation so far.

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it provides 'source-backed information' with 'citations' for transparency, includes 'choices' for diverse perspectives, and warns about 'timeout errors due to long processing times' with a retry suggestion. However, it doesn't cover rate limits, authentication needs, or detailed error handling beyond timeouts.

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

Conciseness3/5

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

The description is front-loaded with the core purpose, but includes a detailed response structure section that repeats information that could be in an output schema. While informative, this adds length without adding proportional value for tool selection. Some sentences could be more concise, but overall it's reasonably structured.

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

Completeness4/5

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

Given the tool's complexity (internet research with potential timeouts) and lack of annotations and output schema, the description does a good job covering key aspects: purpose, behavioral traits like citations and errors, and response structure. However, it could improve by mentioning authentication, rate limits, or more specific use-case boundaries to be fully complete.

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

Parameters3/5

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

The schema description coverage is 100%, so the schema already documents both parameters ('messages' and 'model') thoroughly. The description adds no specific information about parameters beyond what's in the schema, such as format examples or usage tips. 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.

Purpose4/5

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

The description clearly states the tool's purpose: 'gathering source-backed information from the internet' with specific use cases like 'research, fact-checking, or contextual data.' It uses specific verbs like 'gather' and 'equip' and identifies the resource as internet information. However, with no sibling tools mentioned, it cannot demonstrate differentiation from alternatives.

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

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage scenarios ('ideal for scenarios requiring research, fact-checking, or contextual data') but does not provide explicit guidance on when to use this tool versus alternatives. No exclusions or prerequisites are mentioned, and with no sibling tools, there's no comparison to other options.

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 update
    • First observedask_perplexity
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool 'ask_perplexity' has a singular, well-defined purpose for internet research with source-backed information, making it completely distinct by default.

Naming Consistency5/5

The single tool name 'ask_perplexity' follows a clear verb_noun pattern and is the only naming convention present. There are no other tools to compare it to, so consistency is inherently perfect.

Tool Count2/5

A single tool for a server named 'Perplexity MCP Server' feels thin and limited in scope. While the tool is specialized for research, the server's purpose suggests it could benefit from additional tools (e.g., for query refinement, citation management, or batch processing) to provide a more complete research workflow.

Completeness2/5

The tool surface is severely incomplete for a research-oriented server. It only offers a single query function without supporting operations like saving results, managing search history, filtering citations, or handling different query types. This creates significant gaps that will limit agent capabilities in research scenarios.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches