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/jschuller/perplexity-mcp/claude-mdgit clone --depth 1 https://github.com/jschuller/perplexity-mcpWrote 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/jschuller/perplexity-mcp/claude-md)<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="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 | $0.00668 | $0.00668 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 55 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/sdkv1.27+ (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_webwith 12 parameters
Commands
npm run build # Compile TypeScript → dist/
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:
- Bump version in
package.jsonandsrc/index.ts(server version) - Update
CHANGELOG.md - Commit, push to main
- Create GitHub release:
gh release create v2.x.x --title "v2.x.x" --notes "..." - The
publish.ymlworkflow 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
Simple single-file server (src/index.ts):
- Lines 1-11: Imports + API key validation (exits if missing)
- Lines 17-27: Server instance with MCP SDK
Serverclass - Lines 30-108:
ListToolsRequestSchemahandler — defines the tool's JSON Schema - Lines 111-225:
CallToolRequestSchemahandler — builds Perplexity API request, calls API, formats response - Lines 228-232: Stdio transport connection
Key Decisions
- Server class (not McpServer): Uses the lower-level
ServerAPI. Works fine with SDK 1.x. Could migrate toMcpServer+ Zod schemas in a future refactor. - node-fetch: Used instead of native fetch for Node 18 compatibility.
- No tests: Simple wrapper — tested manually via MCP client protocol. CI validates build + audit.
- Granular npm token (not Trusted Publishing): npm doesn't support tokenless OIDC like PyPI. Token is scoped to this package only with 2FA bypass for CI.
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 · 55 lines · 668 tokens per session scan A ed1fb729b23c
perplexity-mcp CLAUDE.md is an instructions file published in the GitHub repository jschuller/perplexity-mcp (6 stars, last pushed 5mo ago), licensed MIT. It adds 668 tokens to every session, about $0.0033 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 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.