perplexity-mcp: Instructions file for Claude Code

CLAUDE.md

perplexity-mcp CLAUDE.md is an instructions file for Claude Code from barankrky/perplexity-mcp. It costs 1,111 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code when working on a Perplexity MCP server, a connector that lets an agent communicate with Perplexity. They cover setup, running the server, cookie handling, testing, and Git steps.

In plain words
What is it for?
Installing dependencies, starting or inspecting the MCP server, exporting and listing saved cookie names, testing with the MCP inspector, and following the repository's Git workflow.
Why use it?
They give the agent the project-specific commands and structure needed to work safely in the repository without guessing how it runs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is barankrky/perplexity-mcp's own configuration. It tells Claude Code how to work on perplexity-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything perplexity-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to barankrky/perplexity-mcp. 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/barankrky/perplexity-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/barankrky/perplexity-mcp

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.

agentmods badge for perplexity-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/barankrky/perplexity-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/barankrky/perplexity-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/barankrky/perplexity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/barankrky/perplexity-mcp/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.

agentmods 80×15 button for perplexity-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/barankrky/perplexity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/barankrky/perplexity-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,111 This file is loaded in full into every session.
When invoked 1,111 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01111 $0.01111
Opus 5.5 $0.00444 $0.00444
Sonnet 5.5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 2mo ago against content hash ff54a96e787e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

perplexity-mcp 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 · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 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

# Install dependencies
pip install -r requirements.txt

# Run the MCP server (stdio transport)
python mcp_server.py

# Export cookies via Playwright (opens browser, log in manually)
pip install playwright
playwright install chromium
python get_cookies.py

# List stored cookie names (without values)
python get_cookies.py --load

# Test with MCP inspector
npx @modelcontextprotocol/inspector python mcp_server.py

# Git workflow (cookie credentials are gitignored)
git status
git add .
git commit -m "message"
git push origin main

Project Structure & Architecture

This is a thin MCP server that wraps Perplexity AI's private internal SSE API, using curl_cffi with Chrome TLS impersonation to bypass Cloudflare.

mcp_server.py            — MCP tool definitions (stdio transport)
    ↑ perplexity_client.py   — HTTP client, SSE parsing, model mapping, payload building
    ↑ cookie_loader.py       — Cookie loading from env var / JSON / HAR / Netscape files
    (get_cookies.py)         — Optional: export cookies via Playwright

Module roles

  • mcp_server.py — Entry point. Registers 5 MCP tools (perplexity_ask, perplexity_search, list_models, reset_conversation, set_cookies). Maintains per-session client/conversation state in module-level dicts. Runs via stdio_server().

  • perplexity_client.py — Core logic. Contains PerplexityClient (HTTP + SSE), PerplexityConversation (multi-turn state), MODEL_MAP (~30 model name translations), and SSE block parsing (markdown_block, diff_block with chunked streaming, sources_answer_mode, media_items, follow-up suggestions). Exposes set_cookies() for runtime cookie updates.

  • cookie_loader.py — Cookie resolution: env var (PERPLEXITY_COOKIES_JSON) > JSON file > HAR file > Netscape-format .txt. Also handles the cookies/perplexity.har path. Exposes parse_cookie_string() for auto-detecting JSON vs Netscape format, used by the set_cookies MCP tool.

Read the full file on GitHub · 81 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.

  1. 2mo ago First seen · 81 lines · 1,111 tokens per session scan A ff54a96e787e

Subscribe to this mod's changes

perplexity-mcp CLAUDE.md is an instructions file published in the GitHub repository barankrky/perplexity-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,111 tokens to every session, about $0.0044 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.

Related

perplexity-mcp CLAUDE.md compared with instructions from other repositories

perplexity-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
perplexity-mcp CLAUDE.mdbarankrky/perplexity-mcpInstructions file03mo agoMITA1,111Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode