PPX-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| perplexity_askA | Ask Perplexity AI a question with real-time web search. Returns an answer synthesized from multiple online sources. |
| perplexity_list_modelsB | List all available Perplexity AI models |
| perplexity_loginA | Opens a browser window to log in to Perplexity and automatically saves cookies. User must complete login in the browser, then the cookies are extracted and saved. |
| perplexity_statusB | Check the status of Perplexity MCP configuration and cookies. |
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: perplexity_ask is for querying, perplexity_list_models for listing models, perplexity_login for authentication, and perplexity_status for configuration checks. There is no overlap in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent 'perplexity_' prefix with descriptive action suffixes (ask, list_models, login, status). This uniform snake_case pattern ensures predictability and readability across the tool set.
With 4 tools, the server is well-scoped for interacting with Perplexity AI, covering essential operations like querying, model listing, authentication, and status checks. Each tool earns its place without being overly sparse or bloated.
The tool set covers core functionalities for a Perplexity AI MCP server, including querying, model discovery, and authentication. A minor gap exists in lacking tools for managing sessions or handling errors, but agents can work around this with the provided tools.