Required for running the MCP server and processing API requests to external services
Leverages Perplexity AI's Sonar models for intelligent search, documentation retrieval, API discovery, and code modernization assistance
Provides documentation and usage examples for React, including analyzing deprecated patterns like class components and suggesting modern alternatives
Uses SQLite database to maintain conversation history for coherent responses across multiple queries
Click on "Deploy 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., "@MCP-researcher Server find APIs for real-time weather data with free tier"
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.
A powerful research assistant that integrates with Cline and Claude Desktop! Leverages Perplexity AI for intelligent search, documentation retrieval, API discovery, and code modernization assistance - all while you code.
Seamless Context Tracking: Maintains conversation history in SQLite database to provide coherent responses across multiple queries
Advanced Query Processing: Uses Perplexity's Sonar models for sophisticated reasoning and detailed answers to complex questions
Intelligent Rate Management: Implements adaptive rate limiting with exponential backoff to maximize API usage without hitting limits
High Performance Networking: Optimizes API calls with connection pooling and automatic retry logic for reliable operation
Related MCP server: Perplexity Tool for Claude Desktop
Performs general search queries to get comprehensive information on any topic. The example shows how to use different detail levels (brief, normal, detailed) to get tailored responses.
Retrieves documentation and usage examples for specific technologies, libraries, or APIs. The example demonstrates getting comprehensive documentation for React hooks, including best practices and common pitfalls.
Discovers and evaluates APIs that could be integrated into a project. The example shows finding payment processing APIs with detailed analysis of features, pricing, and integration complexity.
Analyzes code for deprecated features or patterns, providing migration guidance. The example demonstrates checking React class components and lifecycle methods for modern alternatives.
First install Node.js if not already installed (from nodejs.org)
Clone the repo
Install dependencies and build
Get a Perplexity API key from https://www.perplexity.ai/settings/api
Create the MCP settings file in the appropriate location for your OS:
To use with Claude Desktop, add the server config:
To use with Cline, add into mcpServers:
{
"mcpServers": {
"perplexity-server": {
"command": "node",
"args": ["[path/to/researcher-mcp/build/index.js]"],
"env": {
"PERPLEXITY_API_KEY": "pplx-...",
"PERPLEXITY_MODEL": "sonar-reasoning" // you can use different models
},
"disabled": false,
"alwaysAllow": [],
"autoApprove": [
"search",
"get_documentation",
"find_apis",
"check_deprecated_code",
"get_request_status"
]
}
}
}Build the server: npm run build
Check if code or dependencies might be using deprecated features
Inputs: code (required), technology.
Find and evaluate APIs that could be integrated into a project
Inputs: requirement (required), context.
Get documentation and usage examples for a specific technology, library, or API
Inputs: query (required), context.
Perform a general search query to get comprehensive information on any topic
Inputs: query (required), detail_level.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: checking deprecated code, finding APIs, getting documentation, and performing general searches. The descriptions make it easy for an agent to select the right tool for each specific research task.
Three tools follow a consistent verb_noun pattern (check_deprecated_code, find_apis, get_documentation), but 'search' deviates as a single verb without an object. This minor inconsistency slightly affects predictability, though all names remain readable.
With only 4 tools, the set feels thin for a research server that aims to cover broad information-gathering tasks. While each tool is useful, the scope suggests more specialized research operations could be missing, making it borderline appropriate.
The tools cover key research functions like checking deprecations, finding APIs, getting docs, and general searches, but there are notable gaps. For example, missing tools for comparing technologies, validating information sources, or tracking research progress limit comprehensive workflow coverage.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
