Skip to main content

MS Project MCP Server

Controla o Microsoft Project via automação COM através do Model Context Protocol (MCP).

99 ferramentas para ler, editar e analisar cronogramas direto do seu assistente de IA — sem sair do chat.

Requisitos

Item Detalhe
SO Windows (a automação COM não existe em outros sistemas)
Microsoft Project Instalado e em execução (testado no MS Project 16.0)
Python 3.10 ou superior

Instalação

pip install msproject-mcp

Isso instala as dependências e cria o comando msproject-mcp. Teste que ele sobe:

msproject-mcp

Ele fica aguardando no stdin — é o transporte do MCP. Ctrl+C encerra.

Caminho rápido de leitura opcional (mpxj + JVM; não disponível em Windows ARM64):

pip install "msproject-mcp[fast]"

Antes de usar qualquer ferramenta: o MS Project precisa estar aberto com um arquivo carregado. O servidor se conecta a uma instância já em execução.

Registro no cliente MCP

Claude Code:

claude mcp add msproject --scope user -- msproject-mcp

Claude Desktop — em claude_desktop_config.json:

{
  "mcpServers": {
    "msproject": {
      "command": "msproject-mcp",
      "args": []
    }
  }
}

OpenAI Codex — em ~/.codex/config.toml:

[mcp_servers.msproject]
command = "msproject-mcp"
args = []

Documentação completa

Inventário das 99 ferramentas, convenções da API, testes e limitações conhecidas: github.com/devGPL/MS-Procject-MCP

Metadata

Release files for msproject-mcp 0.7.2

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

Source distribution (sdist)

Source distribution for msproject-mcp 0.7.2
File Size Uploaded Provenance Actions
msproject_mcp-0.7.2.tar.gz 100.2 kB Without provenance Details for msproject_mcp-0.7.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for msproject-mcp 0.7.2
File Interpreter ABI Platform Actions
msproject_mcp-0.7.2-py3-none-any.whl Python 3 none any Details for msproject_mcp-0.7.2-py3-none-any.whl

Total release size: 169.3 kB

Release files / msproject_mcp-0.7.2.tar.gz

Download URL msproject_mcp-0.7.2.tar.gz
Size 100.2 kB
Tags Source
SHA-256 checksum
How to use checksums
178fa41a3a59917cd36b152dc6c2813c870e2b7cf1191e65c7ac6159f214e92e
BLAKE2b-256 checksum
How to use checksums
af57f39da7d9f4229956d366900af4174a88f63026aa257905947da2fd6574c1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.0

Release files / msproject_mcp-0.7.2-py3-none-any.whl

Download URL msproject_mcp-0.7.2-py3-none-any.whl
Size 69.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
370df01c79337024b20b41a132142c0af9b5b7d233ffa13377ed53a1eafe7ade
BLAKE2b-256 checksum
How to use checksums
da5efee30037e114523e019bf61a04195160c11962c402c4ae0fa9a705392cec
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.0

Security for msproject-mcp 0.7.2

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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