Perplexity MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PERPLEXITY_COOKIES | No | Inline JSON string of Perplexity cookies. | |
| PERPLEXITY_COOKIES_PATH | No | Path to a JSON file containing Perplexity cookies. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Search Perplexity AI with the given query. Args: query: The search query string mode: Search mode - 'auto', 'pro', 'reasoning', or 'deep_research' model: Specific model to use (depends on mode): - auto: None - pro: None, 'sonar', 'gpt-4.5', 'gpt-4o', 'claude 3.7 sonnet', 'gemini 2.0 flash', 'grok-2' - reasoning: None, 'r1', 'o3-mini', 'claude 3.7 sonnet' - deep_research: None sources: List of sources to use - 'web', 'scholar', 'social' answer_only: If True, return only answer and backend_uuid. If False, also include sources and related_queries. language: Language code (ISO 639, e.g., 'en-US') incognito: Whether to enable incognito mode Returns: Dictionary with 'answer' and 'backend_uuid'. If answer_only=False, also includes 'sources' and 'related_queries'. |
| follow_upA | Send a follow-up query to continue a previous conversation. Args: query: The follow-up query string backend_uuid: The backend_uuid from the previous response mode: Search mode - 'auto', 'pro', 'reasoning', or 'deep_research' model: Specific model to use (see search tool for options) answer_only: If True, return only answer and backend_uuid. If False, also include sources and related_queries. Returns: Dictionary with 'answer' and 'backend_uuid'. If answer_only=False, also includes 'sources' and 'related_queries'. |
| list_threadsC | List conversation threads from Perplexity AI. Args: limit: Maximum number of threads to return (default 10) search_term: Optional search term to filter threads Returns: Dictionary containing list of threads with their metadata |
| get_threadA | Get details of a specific thread by its slug. Args: slug: The thread slug (identifier from thread URL or list_threads) Returns: Dictionary containing thread details including all messages |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: search for initial queries, follow_up for continuing conversations, list_threads for browsing threads, and get_thread for retrieving full thread details. There is no functional overlap.
All tool names follow a consistent verb_noun snake_case pattern (search, follow_up, list_threads, get_thread), making the set predictable and easy to understand.
With 4 tools, the server is well-scoped for a conversational search assistant, covering essential operations without being too sparse or overwhelming.
The tool set covers the core workflow (search, follow-up, list threads, view details) but lacks delete functionality for threads, which is a minor gap.