Skip to main content

TDN Protheus MCP

MCP público e open source para pesquisar documentação TDN Protheus a partir de um snapshot local controlado pela pessoa usuária. Funciona por stdio, não exige token de LLM e não depende do Chat Protheus IA Lab.

O código usa Apache-2.0. A licença não transfere direitos sobre conteúdo, marcas ou serviços TOTVS/TDN; não publique snapshots nem dados de clientes.

O que ele faz

  • Pesquisa um índice SQLite FTS5 local e devolve citações (source_url, página e chunk).
  • Expõe tools, resources e prompts MCP para qualquer harness compatível com MCP por stdio; Codex e Claude Code são apenas clientes de referência.
  • Inicia offline e read-only. Não baixa documentos durante consultas.
  • A obtenção e atualização do snapshot são capacidades do próprio pacote, sempre acionadas explicitamente.

Início rápido

Depois da publicação no PyPI:

uvx --from "tdn-protheus-mcp[snapshot]" tdn-protheus-mcp doctor --config ./tdn-protheus-mcp.config.json --json
uvx --from "tdn-protheus-mcp[snapshot]" tdn-protheus-mcp index --config ./tdn-protheus-mcp.config.json --root-id 235312129 --json

Copie tdn-protheus-mcp.config.example.json, altere cache_root e, quando quiser atualizar, use apply-refresh com os opt-ins exigidos. Veja instalação, segurança e o contrato MCP.

Skill complementar

A skill portátil coletando-documentacao-tdn-protheus é instalada separadamente e pode criar ou atualizar o mesmo snapshot local que este MCP indexa e consulta. O guia de instalação e operação conjunta cobre Codex, Claude Code, Antigravity e loaders OpenRouter, sem embutir a skill no pacote Python.

Clientes MCP

OpenRouter é um gateway/model provider, não um host MCP por si só. Use-o somente através de um cliente que implemente MCP stdio.

Compatibilidade de harness

O servidor não depende do Chat Protheus IA Lab, de um modelo específico ou de um fornecedor de agentes. Claude Code, Codex, Claude Desktop, Cursor, Cline, IDEs e outros harnesses usam o mesmo processo stdio e contrato. Qualquer ferramenta que produza o formato público de snapshot local pode alimentar o MCP.

Desenvolvimento

python -m pip install -e ".[snapshot]"
python -m unittest discover -s tests -p "test_*.py" -v
python -m build
python -m twine check dist/*

Não envie tdn-cache/, .venv/, snapshots, JSONL, HTML coletado, segredos ou dados de clientes. Consulte CONTRIBUTING.md, SECURITY.md, SUPPORT.md e CHANGELOG.md.

Release files for tdn-protheus-mcp 0.3.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for tdn-protheus-mcp 0.3.1
File Size Uploaded
tdn_protheus_mcp-0.3.1.tar.gz 37.1 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for tdn-protheus-mcp 0.3.1
File Interpreter ABI Platform
tdn_protheus_mcp-0.3.1-py3-none-any.whl Python 3 none any Details

Total release size: 68.4 kB

Release files / tdn_protheus_mcp-0.3.1.tar.gz

Download URL tdn_protheus_mcp-0.3.1.tar.gz
Size 37.1 kB
Tags Source
SHA-256 checksum
How to use checksums
13bbe2e40af82b24da527b27edc3abd145d0ecb95d5845eecaa821a8ad25a5a4
BLAKE2b-256 checksum
How to use checksums
ca9407463474196755d3721fef072e1559ad0dcdeb7ff7350b70fc03938ec666
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 16, 2026.

Transparency log

Release files / tdn_protheus_mcp-0.3.1-py3-none-any.whl

Download URL tdn_protheus_mcp-0.3.1-py3-none-any.whl
Size 31.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
390c1f15a72d4c126cb66314265e5348c2e3be1f4943ab37f6b2eefa110b79fa
BLAKE2b-256 checksum
How to use checksums
729a65812973d29a8c41e24422fbe814d3570f67c1a317fc49a1130fa8191e0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Aug 16, 2026.

Transparency log

Release history Release notifications | RSS feed

0.4.1

2 release files

0.4.0

2 release files

This release

0.3.1 This release

2 release files

0.3.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page