Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/escapewu/perplexity-ai/claude-mdgit clone --depth 1 https://github.com/escapeWu/perplexity-aiWrote 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.
[](https://agentmods.dev/instructions/escapewu/perplexity-ai/claude-md)<a href="https://agentmods.dev/instructions/escapewu/perplexity-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/escapewu/perplexity-ai/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00504 | $0.00504 |
| Opus 5 | $0.00252 | $0.00252 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
perplexity-ai 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 4d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Perplexity MCP Server - An unofficial Python API for Perplexity.ai that exposes search capabilities via MCP (Model Context Protocol) and OpenAI-compatible endpoints. Supports multi-token pools for load balancing, health monitoring, and various search modes.
Commands
# Install dependencies
uv sync
# Run the server (default: HTTP on port 8000)
uv run perplexity
# Run with specific transport
uv run perplexity --transport http --host 0.0.0.0 --port 8000
# Run tests
uv run pytest
# Run a single test file
uv run pytest tests/test_client_pool.py
# Run with coverage
uv run pytest --cov=perplexity
# Format code
uv run black perplexity tests
uv run isort perplexity tests
# Docker deployment
docker compose up -d
Architecture
Core Flow: main.py → app.py (FastMCP instance + middleware) → route modules (mcp.py, oai.py, admin.py)
Key Components:
perplexity/server/app.py- FastMCP app, auth middleware,run_query()core logic, ClientPool singletonperplexity/server/mcp.py- MCP tool definitions:list_models,search,researchperplexity/server/oai.py- OpenAI-compatible API:/v1/models,/v1/chat/completionsperplexity/server/admin.py- Health check, token pool management, heartbeat controlperplexity/server/client_pool.py- Multi-account connection pool with load balancing and exponential backoffperplexity/client.py- Low-level Perplexity API client using WebSocket
Configuration:
token_pool_config.json- Token pool and heartbeat settings- Environment variables:
MCP_TOKEN,PPLX_ADMIN_TOKEN,SOCKS_PROXY
Code Style
- Line length: 100 characters (black/isort configured in pyproject.toml)
- Python 3.10+
- Use type hints where appropriate
Web Search
Use perplexity-mcp tools instead of webSearch for web search functionality.
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.
- 4d ago First seen · 63 lines · 504 tokens per session scan A 652da4441372
perplexity-ai CLAUDE.md is an instructions file published in the GitHub repository escapeWu/perplexity-ai (165 stars, last pushed 16d ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
ha-indygo-pool AGENTS.md
Instructions for FunFR/ha-indygo-pool, covering agents.md, 🧠 philosophy & principles, 📂 project structure & responsibilities, 🔄 development workflow and 🚀 getting a fix to a reporter.
ha-indygo-pool CLAUDE.md
Instructions for FunFR/ha-indygo-pool, a project described as: A Home Assistant Integration for Indygo connected pool solution.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.