Borrowing it
Nothing to install: this file belongs to SEI-Pro/mcp-seipro. 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/SEI-Pro/mcp-seipro/main/CLAUDE.mdgit clone --depth 1 https://github.com/SEI-Pro/mcp-seiproWrote 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/sei-pro/mcp-seipro/claude-md)<a href="https://agentmods.dev/instructions/sei-pro/mcp-seipro/claude-md"><img src="https://agentmods.dev/badge/instructions/sei-pro/mcp-seipro/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/sei-pro/mcp-seipro/claude-md"><img src="https://agentmods.dev/badge/instructions/sei-pro/mcp-seipro/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 | $0.07366 | $0.07366 |
| Opus 5.5 | $0.02946 | $0.02946 |
| Sonnet 5.5 | $0.01473 | $0.01473 |
| Haiku 4.5 | $0.00737 | $0.00737 |
Grade A, and why
mcp-seipro 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 6d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-seipro — Contexto para Claude Code
O que é
MCP Server para o SEI (Sistema Eletrônico de Informações) via API REST mod-wssei v2 + scraper HTTP do frontend web (modo híbrido). ~116 tools cobrindo processos, documentos, tramitação, assinatura, blocos, marcadores, acompanhamento, credenciamento, modelos e mais. Funciona com qualquer instância SEI que tenha o módulo mod-wssei v2 instalado.
Stack
- Python 3.11+, FastMCP (mcp SDK 1.12+), httpx, BeautifulSoup, markdownify, pdfplumber, pytesseract
- Transport: stdio (local) ou Streamable HTTP + OAuth (remoto:
https://mcp.seipro.io, na VPS KVM4) - Configuração: variáveis de ambiente (SEI_URL, SEI_USUARIO, SEI_SENHA, SEI_ORGAO)
Produção (mcp.seipro.io)
- Roda na VPS Hostinger KVM4 desde 2026-10-24: pilha em
/srv/mcp-seipro, publicação com/srv/mcp-seipro/deploy/deploy.sh [commit]como root, depois degit pullno clone/home/pedro/mcp-seipro. Arranjo completo emdeploy/README.md. - Nunca
railway upno projetomcp-seiprodo Railway: o serviço de lá é o proxy de transição (deploy/railway-proxy/), e o upload do código abriria um segundo servidor com outroJWT_SECRET. JWT_SECRET(em/srv/mcp-seipro/env/app.env) sela tokens e clientes OAuth: trocá-lo desconecta todo mundo. O guia de Railway do README é para instâncias de terceiros.- DNS de
seipro.iona Cloudflare (token em~/.config/cloudflare/pedrohsoares.envno Mac do Pedro).
Arquivos principais
src/mcp_seipro/server.py— FastMCP server com ~116 tools + helpers (_resolver_documento, _resolver_processo)src/mcp_seipro/sei_client.py— Cliente REST assíncrono para mod-wssei v2 (auth automática, auto-reauth 401/403, cache de metadados TTL 1h)src/mcp_seipro/sei_web_client.py— Cliente HTTP scraper do frontend web do SEI (login SIP, sessão persistente, parser de inbox/árvore/histórico)src/mcp_seipro/html_utils.py— html_to_text, html_to_markdown, pdf_to_text, pdf_to_markdown (com OCR fallback), sanitize_iso8859src/mcp_seipro/sei_styles.py— Dicionário de 39 estilos CSS do SEI + helpers (html_referencia_sei, html_destinatario)
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.
- 6d ago Changed · +7 lines · +240 tokens per session 61a57aeda844
- 1mo ago Changed · +1 lines · +221 tokens per session 10535386a6ac
- 1mo ago Changed · +8 lines · +355 tokens per session 9500e14cfc78
- 2mo ago First seen · 165 lines · 6,550 tokens per session scan A 09036ac38e29
mcp-seipro CLAUDE.md is an instructions file published in the GitHub repository SEI-Pro/mcp-seipro (20 stars, last pushed 6d ago), licensed MIT. It adds 7,366 tokens to every session, about $0.0295 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.
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).
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.
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).
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 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).
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.