perplexity-mcp: Instructions file for Claude Code

CLAUDE.md

perplexity-mcp CLAUDE.md is an instructions file for Claude Code from jschuller/perplexity-mcp. It costs 845 tokens per session, scanned A, original, MIT.

Project instructions for a TypeScript server that connects Claude to Perplexity AI's web-search service. They describe the project structure, commands, architecture, and release process.

In plain words
What is it for?
Use them when developing the server, running its build or audit commands, or preparing an automated npm release.
Why use it?
They give contributors the project-specific context needed to build, test, audit, and release the server consistently.

Instructions file for Claude Code

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

This is jschuller/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 jschuller/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/jschuller/perplexity-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jschuller/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/jschuller/perplexity-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jschuller/perplexity-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jschuller/perplexity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jschuller/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/jschuller/perplexity-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jschuller/perplexity-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 845 This file is loaded in full into every session.
When invoked 845 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 $0.00845 $0.00845
Opus 5.5 $0.00338 $0.00338
Sonnet 5.5 $0.00169 $0.00169
Haiku 4.5 $0.00085 $0.00085

Measured 14d ago against content hash 599261b8ff8a, 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 14d 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 · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Perplexity MCP Server

Project Overview

MCP server that connects Claude (Desktop/Code) to Perplexity AI's web search API. Published as @jschuller/perplexity-mcp on npm. ~200 monthly downloads, 6 stars.

  • Language: TypeScript (strict mode)
  • Transport: stdio (MCP standard)
  • SDK: @modelcontextprotocol/sdk v1.27+ (upgraded from 0.5.0 in v2.1.0)
  • Entry points: bin.js (npm/npx) → dist/index.js (compiled) ← src/index.ts (source)
  • One tool: perplexity_search_web with 12 parameters

Commands

npm run build        # Compile TypeScript → dist/
npm test             # node --test against dist/ (build first)
npm run start        # Run locally with .env
npm publish          # Publish to npm (use GitHub release instead — triggers CI)
npm audit            # Check for dependency vulnerabilities

Release Process

Releases are automated via GitHub Actions:

  1. Bump version in package.json and src/index.ts (server version)
  2. Update CHANGELOG.md
  3. Commit, push to main
  4. Create GitHub release: gh release create v2.x.x --title "v2.x.x" --notes "..."
  5. The publish.yml workflow auto-publishes to npm with provenance

npm token: Granular access token (perplexity-mcp-publish) stored as NPM_TOKEN secret. Scoped to this package only, expires June 2026. Renew at npmjs.com/settings/jschuller/tokens.

Architecture

  • src/index.ts: API key check (exits if missing), the MCP Server, the tool's JSON Schema (tools/list), the tools/call handler, and the stdio transport
  • src/search.ts: one search call: argument checks, the API request with a timeout (PERPLEXITY_TIMEOUT_MS, default 60 s), and every failure returned as a tool result with isError: true; fetch is injected so tests mock it
  • src/perplexity.ts: pure helpers that build the request body and format the response

Key Decisions

  • Server class (not McpServer): Uses the lower-level Server API. Works fine with SDK 1.x. Could migrate to McpServer + Zod schemas in a future refactor.
  • node-fetch: Used instead of native fetch for Node 18 compatibility.
  • Tests: npm test (after npm run build) runs node --test on tests/perplexity.test.mjs (the pure request/response helpers in src/perplexity.ts plus stdio tools/list and tools/call smoke tests) and tests/search.test.mjs (src/search.ts with a mocked fetch: errors, timeouts, bad responses); no API key or network. CI runs build + test + audit.
  • npm Trusted Publishing (OIDC): publish.yml publishes with the job's OIDC token and no npm token (the repository has no secrets); npm documents it as needing npm 11.5.1+ and Node 22.14.0+ (the workflow pins npm 11.21.0 and Node 22.23.3).

Read the full file on GitHub · 56 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. 14d ago Changed · +52 tokens per session 599261b8ff8a
  2. 15d ago Changed · +62 tokens per session 517cb922b006
  3. 17d ago Changed · +1 lines · +63 tokens per session 201367af3db1
  4. 2mo ago First seen · 55 lines · 668 tokens per session scan A ed1fb729b23c

Subscribe to this mod's changes

perplexity-mcp CLAUDE.md is an instructions file published in the GitHub repository jschuller/perplexity-mcp (6 stars, last pushed 2d ago), licensed MIT. It adds 845 tokens to every session, about $0.0034 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

Other instructions, from other repositories

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).

microsoft/vscode · 9,719 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,516 tokens

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.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,313 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 3,037 tokens