Connect Perplexity Ai to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.
Ask your agent in plain language. Each of these maps to a real tool on the server.
Use the agent completion tool in Perplexity Ai
Use the sonar chat completion tool in Perplexity Ai
Use the web search tool in Perplexity Ai
Use the generate embeddings tool in Perplexity Ai
Supported Tools
agent_completion
Agent Completion
Execute agentic AI workflows through Perplexity's Agent API, which provides unified access to models from OpenAI, Anthropic, Google, xAI, NVIDIA, and Perplexity through a single request.
Supports built-in tools (web search, URL fetching), model fallback chains, and pre-configured **presets** for common use cases:
- **fast-search** - Quick factual lookups (xAI Grok, 1 step)
- **pro-search** - Balanced research (GPT-5.1, 3 steps)
- **deep-research** - Multi-source analysis (GPT-5.2, 10 steps)
- **advanced-deep-research** - Expert research (Claude Opus, 10 steps)
You can use presets as-is or override any parameter. Models use the `provider/model-name` format (e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4-6`).
chat_completion
Sonar Chat Completion
Generate AI responses grounded in real-time web search using Perplexity's Sonar models. Responses include inline citations to web sources, making it ideal for factual queries, research summaries, and question answering.
Available models:
- **sonar** - Lightweight, fast search model for quick queries
- **sonar-pro** - Advanced model with multi-step queries and ~2x more citations
- **sonar-reasoning-pro** - Chain-of-thought reasoning for complex analysis
- **sonar-deep-research** - Expert-level exhaustive research and reports
Supports search filters (domain, recency, language), structured JSON output, and optional image/related question retrieval.
web_search
Web Search
Perform raw web searches using Perplexity's search index covering hundreds of billions of webpages. Returns ranked results with pre-extracted snippets, ready for use in RAG pipelines or custom synthesis workflows.
Unlike chat completions, this returns **raw search results** without AI-generated summaries, giving you full control over how results are processed and presented.
Supports domain filtering, date filtering, recency filtering, language filtering, and location-based search.
generate_embeddings
Generate Embeddings
Generate vector embeddings for text using Perplexity's pplx-embed models. Useful for semantic search, clustering, retrieval-augmented generation (RAG), and recommendation systems.
Available models:
- **pplx-embed-v1-0.6b** - Lightweight, low-latency (1024 dimensions)
- **pplx-embed-v1-4b** - Higher quality retrieval (2560 dimensions)
- **pplx-embed-context-v1-0.6b** - Contextualized, lightweight (1024 dimensions)
- **pplx-embed-context-v1-4b** - Contextualized, higher quality (2560 dimensions)
Standard models are best for independent texts and search queries. Contextualized models are optimized for document chunks that benefit from surrounding context. All models produce INT8-quantized embeddings natively.
Enable Perplexity Ai in Metorial. In your Metorial portal, enable the Perplexity Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
Sign in. Select Add and sign in to load Perplexity Ai tools.
Enable Perplexity Ai in Metorial. In your Metorial portal, enable the Perplexity Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add a custom MCP server. On ChatGPT web, open Plugins, select +, then Add custom MCP server.
Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.
Create and install the plugin. Select Create as a plugin, install it and sign in to load Perplexity Ai tools.
Enable Perplexity Ai in Metorial. In your Metorial portal, enable the Perplexity Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add Metorial to your MCP config. Use ~/.cursor/mcp.json for every project, or .cursor/mcp.json for one.
Sign in. Open Customize in the sidebar, find Metorial and sign in to load Perplexity Ai tools.
{
"mcpServers":{
"metorial":{
"url":"<your-magic-mcp-url>"
}
}
}
Enable Perplexity Ai in Metorial. In your Metorial portal, enable the Perplexity Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server over HTTP. Add --scope user to use it in every project.
Sign in. Run /mcp, select Metorial and sign in to load Perplexity Ai tools.
claude mcp add --transport http metorial <your-magic-mcp-url>
Enable Perplexity Ai in Metorial. In your Metorial portal, enable the Perplexity Ai MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
Add the server and sign in. The Codex CLI, IDE extension and ChatGPT desktop app share this config.
Check the connection. Type /mcp in Codex to see Metorial and its Perplexity Ai tools.
codex mcp add metorial --url <your-magic-mcp-url>
codex mcp login metorial
Run Perplexity Ai through the Metorial gateway
One governed layer for every app your agents reach, not a separate connector per tool.
Give Perplexity Ai and every other app to your whole team through one MCP gateway, behind your SSO.
Scope which teams and agents can use Perplexity Ai tools with role-based access control, and trace every call.
Prefer to run it yourself? Metorial is open source and self-hostable.
Perform AI-powered web searches and generate grounded answers with citations. Access multiple LLM providers (OpenAI, Anthropic, Google, xAI, Sonar) through a unified chat completions interface. Retrieve raw ranked web search results for RAG pipelines. Generate text embeddings for semantic search and retrieval. Supports streaming responses, structured JSON output, search recency and domain filtering, multi-step reasoning, deep research reports, model fallback, and configurable presets for common workflows. Manage API keys and groups programmatically.
Frequently asked questions
Common questions about connecting Perplexity Ai to AI agents with Metorial.
How many tools does the Perplexity Ai MCP server have?
The Perplexity Ai MCP server exposes 4 tools, including Agent Completion, Sonar Chat Completion, Web Search. Each one is governed and traced through Metorial.
Does the Perplexity Ai MCP server support triggers?
Perplexity Ai exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
Which AI clients can use the Perplexity Ai MCP server?
Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Perplexity Ai MCP server through the same Metorial URL.
How do I give only some teams access to Perplexity Ai?
Use role-based access control to decide which teams, users, and agents can use Perplexity Ai and which of its tools they can call.
Can I self-host the Perplexity Ai MCP server?
Yes. Metorial is open source, so you can run the Perplexity Ai MCP server yourself or use the hosted gateway.
Connect Perplexity Ai to production AI agents
See how Metorial gives your team governed access to Perplexity Ai, with tracing and security controls built in.