perplexity-agent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PERPLEXITY_API_KEY | Yes | Your Perplexity API key. Required. | |
| PERPLEXITY_AGENT_WAIT_SECONDS | No | Seconds a blocking tool call may wait before handing back a response_id instead of an answer. Default is 55. Valid positive values are capped at 1800. | 55 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| perplexity_agentA | Run a research query through Perplexity's Agent API (multi-step web research with citations). Use for deep or multi-hop questions where a single synthesized, sourced answer is wanted. With wait=true (default) this blocks until the answer is ready; if it takes too long you get a response_id to collect later with perplexity_agent_result. |
| perplexity_agent_resultA | Retrieve the result of a research run started by perplexity_agent. If it is still running, reports what it has done so far and how to check again. |
| perplexity_agent_cancelA | Ask Perplexity to stop a research run that is no longer needed. Perplexity does not report usage for cancelled runs, so this cannot tell you whether it changed your bill. |
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 3 tools
Each tool has a distinct role: one starts a research run, one retrieves results, and one cancels. The descriptions clearly differentiate their purposes, leaving no ambiguity.
All tools share the 'perplexity_agent' prefix, but the main tool lacks a verb suffix while the others have '_cancel' and '_result'. This is a minor deviation from a fully consistent verb_noun pattern.
Three tools perfectly cover the core operations for running and managing research queries via the Perplexity Agent API. The count is well-scoped and not excessive.
The tool set covers the full lifecycle: start a run, retrieve results, and cancel if needed. There are no obvious missing operations for this domain.