Borrowing it
Nothing to install: this file belongs to cfdude/mcp-perplexity-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cfdude/mcp-perplexity-pro/main/CLAUDE.mdgit clone --depth 1 https://github.com/cfdude/mcp-perplexity-proWrote 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/cfdude/mcp-perplexity-pro/claude-md)<a href="https://agentmods.dev/instructions/cfdude/mcp-perplexity-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/cfdude/mcp-perplexity-pro/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.
<a href="https://agentmods.dev/instructions/cfdude/mcp-perplexity-pro/claude-md"><img src="https://agentmods.dev/badge/instructions/cfdude/mcp-perplexity-pro/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.19622 | $0.19622 |
| Opus 5.5 | $0.07849 | $0.07849 |
| Sonnet 5.5 | $0.03924 | $0.03924 |
| Haiku 4.5 | $0.01962 | $0.01962 |
Grade A, and why
mcp-perplexity-pro 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 — 844 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.
MCP server for the Perplexity API, written in Python (FastMCP, SQLAlchemy 2.0 async, SQLite,
Alembic). Version 2.0.0 replaced the TypeScript 1.x server, which is deleted (git history keeps
it): Perplexity retired the Sonar endpoints (403 chat_completions_not_available), so there was
nothing to port. Eleven tools exist: perplexity_help (free, the server's own help: index, tool, topic), the four Agent API tools perplexity_ask, perplexity_chat,
perplexity_research and perplexity_jobs (they spend money), perplexity_search (the Search
API, one costed request per call), perplexity_decide (the Decisions API, one costed request per
call), perplexity_embed (the Embeddings API: index, search, status and delete over a local
vector store, one costed request per batch or search), plus perplexity_models,
perplexity_projects and the read-only perplexity_usage. All four Perplexity APIs now have a
tool, and every costed call is recorded (see "How to record usage"). Read README.md for the
user-facing behavior and openspec/changes/archive/2026-10-09-py-foundation/,
openspec/changes/archive/2026-10-09-py-usage-log/,
openspec/changes/archive/2026-10-09-py-agent-api/,
openspec/changes/archive/2026-10-11-py-search-api/,
openspec/changes/archive/2026-10-11-py-decisions-tool/ and
openspec/changes/archive/2026-10-11-py-embeddings/ (design.md especially) for why things are the way they are.
Development Commands
Python 3.12+, uv. Never use pip, bare python or a hand-made venv.
uv sync # install from uv.lock (runtime + dev)
uv run mcp-perplexity-pro --transport stdio # or: --transport http (127.0.0.1:8102/mcp)
uv run perplexity-pro help # the command line front end (also: ask, search, usage, serve ...)
uv run pytest # offline suite, about 60 s
uv run pytest tests/test_catalog.py -k stale # one file / one test
uv run ruff check . # lint
uv run ruff format --check . # formatting (use `uv run ruff format .` to fix)
uv run pre-commit run --all-files # what the commit hook runs
PERPLEXITY_API_KEY=... uv run pytest -m live # live tests; real key, never committed
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 Changed · +7 lines · +197 tokens per session 010a2fc8f034
- 6d ago Changed · +238 tokens per session aafad04c3147
- 19d ago Changed · +8 lines · +689 tokens per session 4b9536219c22
- 21d ago Changed · +2 lines · +356 tokens per session 12fd1c6ecfa4
- 22d ago Changed · -14 tokens per session 4b2a22c61072
- 23d ago Changed · +73 lines · +2,262 tokens per session 5a5e40f9d7f8
- 26d ago Changed · +60 lines · +2,363 tokens per session f722a964ab13
- 27d ago Changed · +507 lines · +12,332 tokens per session ce8985e5ddc9
- 2mo ago First seen · 187 lines · 1,199 tokens per session scan A a560cf18c88a
mcp-perplexity-pro CLAUDE.md is an instructions file published in the GitHub repository cfdude/mcp-perplexity-pro (3 stars, last pushed 5d ago), licensed MIT. It adds 19,622 tokens to every session, about $0.0785 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-perplexity-pro CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-perplexity-pro CLAUDE.mdcfdude/mcp-perplexity-pro | Instructions file | 3 | 5d ago | MIT | A | 19,622 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |