Use them when setting up the project, starting development, building it, formatting code, or configuring which research and reasoning models are enabled.

They document the required API key, available settings, package commands, and the main server components needed to work on the project.

How elct9620/perplexity-ask-openrouter configures Claude Code

Q: What is perplexity-ask-openrouter CLAUDE.md?

Repository instructions for an MCP server that provides access to Perplexity AI models through OpenRouter, a service that connects applications to different AI models.

Reuse

Borrowing it

Nothing to install: this file belongs to elct9620/perplexity-ask-openrouter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/elct9620/perplexity-ask-openrouter/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/elct9620/perplexity-ask-openrouter

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/elct9620/perplexity-ask-openrouter/claude-md/github.svg)](https://agentmods.dev/instructions/elct9620/perplexity-ask-openrouter/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/elct9620/perplexity-ask-openrouter/claude-md"><img src="https://agentmods.dev/badge/instructions/elct9620/perplexity-ask-openrouter/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/elct9620/perplexity-ask-openrouter/claude-md"><img src="https://agentmods.dev/badge/instructions/elct9620/perplexity-ask-openrouter/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 989 This file is loaded in full into every session.

When invoked 989 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00989	$0.00989
Opus 5.5	$0.00396	$0.00396
Sonnet 5.5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 2mo ago against content hash f59736bb1b72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

perplexity-ask-openrouter CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

Development

pnpm dev - Start development mode with file watching
pnpm build - Build for production

Package Management

Use pnpm (not npm/yarn) - this project uses pnpm v10.11.0

Code Formatting

pnpm prettier --write . - Format code (Prettier is configured)

Environment Setup

Required environment variable:

OPENROUTER_API_KEY - OpenRouter API key for accessing Perplexity models

Optional environment variables:

PORT (default: 3000)
ASK_MODEL, RESEARCH_MODEL, REASON_MODEL - Custom model configurations
DISABLE_ASK, DISABLE_RESEARCH, DISABLE_REASON - Feature toggles

Architecture Overview

This is a Model Context Protocol (MCP) server that provides access to Perplexity AI models through OpenRouter's API. The architecture follows these key patterns:

Core Components

Server.ts - Main MCP server implementation (PerplexityAskServer)
Container.ts - Simple dependency injection container
Config.ts - Environment-based configuration management
OpenRouterAskTool.ts - OpenRouter API integration
ToolDefinition.ts - Defines three MCP tools for different Perplexity models

Transport Layer

The server supports dual transport architecture:

SSE (Server-Sent Events) - Custom implementation for legacy compatibility
Streamable HTTP - Official @hono/mcp transport for modern MCP clients
Transport tracking through dedicated repository pattern

Tool Architecture

Three distinct tools are provided:

perplexity_ask - General Q&A with sonar-pro model
perplexity_research - Deep research with sonar-deep-research model
perplexity_reason - Complex reasoning with sonar-reasoning-pro model

Each tool can be individually disabled via environment variables.

Key Patterns

Repository Pattern - Both SseTransportRepository and McpTransportRepository manage transport lifecycle
Dual Transport Strategy - SSE for legacy, @hono/mcp for modern clients
Dependency Injection - Simple container-based DI in Container.ts
Environment Configuration - All config through environment variables

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 131 lines · 989 tokens per session scan A f59736bb1b72

Subscribe to this mod's changes

perplexity-ask-openrouter CLAUDE.md is an instructions file published in the GitHub repository elct9620/perplexity-ask-openrouter (8 stars, last pushed 8mo ago), licensed MIT. It adds 989 tokens to every session, about $0.0040 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

mcp-server openrouter perplexity

perplexity-ask-openrouter CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
perplexity-ask-openrouter CLAUDE.mdelct9620/perplexity-ask-openrouter	Instructions file	8	8mo ago	MIT	A	989	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	today	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

perplexity-ask-openrouter: Instructions file for Claude Code