Can I use Perplexity AI as a CLI?

Yes. KosmoKrator exposes a Perplexity AI CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Perplexity AI through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Perplexity AI tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Perplexity AI credentials stored?

Perplexity AI credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Perplexity AI MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

Perplexity AI CLI for AI Agents

Use the Perplexity AI CLI from KosmoKrator to call Perplexity AI tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

4 functions 4 read 0 write API key auth

Submit Perplexity AI feedback View package source

Perplexity AI CLI Setup

Perplexity AI can be configured headlessly with `kosmokrator integrations:configure perplexity`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure perplexity --set api_key="$PERPLEXITY_API_KEY" --enable --read allow --write ask --json
kosmokrator integrations:doctor perplexity --json
kosmokrator integrations:status --json

Credentials

Authentication type: API key api_key. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`api_key`	`PERPLEXITY_API_KEY`	Secret `secret`	yes	API Key
`url`	`PERPLEXITY_URL`	URL `url`	no	API Base URL

Call Perplexity AI Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call perplexity.perplexity_chat '{
  "messages": "example_messages",
  "model": "example_model",
  "temperature": 1,
  "max_tokens": 1,
  "search_domain_filter": "example_search_domain_filter",
  "return_images": true,
  "return_related_questions": true,
  "search_recency_filter": "example_search_recency_filter"
}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:perplexity perplexity_chat '{
  "messages": "example_messages",
  "model": "example_model",
  "temperature": 1,
  "max_tokens": 1,
  "search_domain_filter": "example_search_domain_filter",
  "return_images": true,
  "return_related_questions": true,
  "search_recency_filter": "example_search_recency_filter"
}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs perplexity --json
kosmo integrations:docs perplexity.perplexity_chat --json
kosmo integrations:schema perplexity.perplexity_chat --json
kosmo integrations:search "Perplexity AI" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Perplexity AI.

`perplexity.perplexity_chat`

Read read

Send messages to Perplexity AI for a chat completion response. Supports multi-turn conversations with message history. Returns the assistant response with optional citations and search results.

Parameters: messages, model, temperature, max_tokens, search_domain_filter, return_images, return_related_questions, search_recency_filter

Generic CLI call

kosmo integrations:call perplexity.perplexity_chat '{"messages":"example_messages","model":"example_model","temperature":1,"max_tokens":1,"search_domain_filter":"example_search_domain_filter","return_images":true,"return_related_questions":true,"search_recency_filter":"example_search_recency_filter"}' --json

Provider shortcut

kosmo integrations:perplexity perplexity_chat '{"messages":"example_messages","model":"example_model","temperature":1,"max_tokens":1,"search_domain_filter":"example_search_domain_filter","return_images":true,"return_related_questions":true,"search_recency_filter":"example_search_recency_filter"}' --json

`perplexity.perplexity_ask`

Read read

Ask Perplexity AI a question and get a concise answer with cited sources. Best for factual queries, research, and knowledge questions.

Parameters: query, model, temperature, max_tokens, search_domain_filter, return_images, return_related_questions, search_recency_filter

Generic CLI call

kosmo integrations:call perplexity.perplexity_ask '{"query":"example_query","model":"example_model","temperature":1,"max_tokens":1,"search_domain_filter":"example_search_domain_filter","return_images":true,"return_related_questions":true,"search_recency_filter":"example_search_recency_filter"}' --json

Provider shortcut

kosmo integrations:perplexity perplexity_ask '{"query":"example_query","model":"example_model","temperature":1,"max_tokens":1,"search_domain_filter":"example_search_domain_filter","return_images":true,"return_related_questions":true,"search_recency_filter":"example_search_recency_filter"}' --json

`perplexity.perplexity_list_models`

Read read

List all available Perplexity AI models. Returns model IDs and their capabilities for use in chat and ask tools.

Parameters: none

Generic CLI call

kosmo integrations:call perplexity.perplexity_list_models '{}' --json

Provider shortcut

kosmo integrations:perplexity perplexity_list_models '{}' --json

`perplexity.perplexity_get_current_user`

Read read

Get information about the currently authenticated Perplexity API user, including account details and usage.

Parameters: none

Generic CLI call

kosmo integrations:call perplexity.perplexity_get_current_user '{}' --json

Provider shortcut

kosmo integrations:perplexity perplexity_get_current_user '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`perplexity.perplexity_chat`

Send messages to Perplexity AI for a chat completion response. Supports multi-turn conversations with message history. Returns the assistant response with optional citations and search results.

Operation: Read read
Schema command: kosmo integrations:schema perplexity.perplexity_chat --json

Parameter	Type	Required	Description
`messages`	array	yes	Array of message objects, each with "role" (system, user, or assistant) and "content" (string). Example: [{"role": "user", "content": "What is AI?"}].
`model`	string	no	Model to use: "sonar" (fast, lightweight), "sonar-pro" (advanced), "sonar-reasoning" (reasoning), or "sonar-reasoning-pro" (advanced reasoning). Defaults to "sonar".
`temperature`	number	no	Sampling temperature (0.0–2.0). Lower values are more focused, higher values more creative. Defaults to 0.2.
`max_tokens`	integer	no	Maximum number of tokens in the response.
`search_domain_filter`	array	no	List of domains to limit search results to (e.g., ["wikipedia.org"]). Pass empty array to exclude, or omit for no filter.
`return_images`	boolean	no	Whether to return images in the response. Defaults to false.
`return_related_questions`	boolean	no	Whether to return related questions. Defaults to false.
`search_recency_filter`	string	no	Filter search results by recency: "month", "week", "day", or "hour".

`perplexity.perplexity_ask`

Ask Perplexity AI a question and get a concise answer with cited sources. Best for factual queries, research, and knowledge questions.

Operation: Read read
Schema command: kosmo integrations:schema perplexity.perplexity_ask --json

Parameter	Type	Required	Description
`query`	string	yes	The question or prompt to ask Perplexity AI.
`model`	string	no	Model to use: "sonar", "sonar-pro", "sonar-reasoning", or "sonar-reasoning-pro". Defaults to "sonar".
`temperature`	number	no	Sampling temperature (0.0–2.0). Lower values are more focused. Defaults to 0.2.
`max_tokens`	integer	no	Maximum number of tokens in the response.
`search_domain_filter`	array	no	List of domains to limit search results to (e.g., ["wikipedia.org"]).
`return_images`	boolean	no	Whether to return images in the response. Defaults to false.
`return_related_questions`	boolean	no	Whether to return related questions. Defaults to false.
`search_recency_filter`	string	no	Filter search results by recency: "month", "week", "day", or "hour".

`perplexity.perplexity_list_models`

List all available Perplexity AI models. Returns model IDs and their capabilities for use in chat and ask tools.

Operation: Read read
Schema command: kosmo integrations:schema perplexity.perplexity_list_models --json

Parameter	Type	Required	Description
No parameters.

`perplexity.perplexity_get_current_user`

Get information about the currently authenticated Perplexity API user, including account details and usage.

Operation: Read read
Schema command: kosmo integrations:schema perplexity.perplexity_get_current_user --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.