convez.ai
MCP ServerAutomaçãoIntermediário
arikanatakan

pmcontrols-mcp

arikanatakan/pmcontrols-mcp

Análise de projetos validada e confiável para agentes IA

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que expõe a biblioteca validada pmcontrols como ferramentas para agentes IA, oferecendo análises de gestão de projetos (CPM, PERT, EVM, earned schedule) e geração de gráficos (Gantt, rede, S-curve). Garante cálculos determinísticos e confiáveis de métricas de projeto, deixando o agente focar em análise e interpretação.

Instalação

$npx convez-ai arikanatakan/pmcontrols-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
4
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Planejamento e replano de cronogramas de projeto com análise de caminho crítico
  • Análise de valor agregado (EVM) e previsão de conclusão de projetos
  • Avaliação de riscos de cronograma via simulação Monte Carlo (PERT)
  • Otimização de cronogramas sob restrição de custo (crashing)
  • Geração de relatórios visuais (Gantt, rede, S-curve, criticidade)

Veredito

Ferramenta sólida para automatizar cálculos de gestão de projetos em agentes IA, eliminando erros manuais comuns. Ideal para times que precisam de métricas confiáveis e gráficos prontos a partir de dados de projeto estruturados.

README

A tradução para o português deste README ainda está na fila.

pmcontrols-mcp

CI PyPI License: MIT

An MCP server that exposes pmcontrols, the validated project scheduling and earned value library for Python, as tools for AI agents: from critical-path and earned-value analysis to ready-to-show charts (Gantt, network, S-curve, criticality, completion histogram).

Agents asked to plan a project or report its status tend to generate the arithmetic themselves: a backward pass done by eye, an earned-value index inverted, an earned schedule mistaken for schedule variance. Generated project metrics fail silently. The calculation belongs in a deterministic, versioned, validated library that the agent calls, which leaves the agent to choose the analysis and explain the result.

pmcontrols-mcp architecture: an AI agent calls the server's analysis and chart tools, which route to the validated pmcontrols core and return structured JSON or PNG images

Tools

Analysis tools return the library's structured payload: named statistics, a tidy table, structured alerts, and provenance (library version, input hash, timestamp).

ToolPurpose
critical_pathCPM forward and backward pass: ES, EF, LS, LF, slack, critical path
schedule_riskPERT three-point analysis with a Monte Carlo completion distribution and criticality indices
crash_scheduleminimum-cost schedule compression to a deadline, solved as a linear program
earned_valuethe full EVM indicator set with Lipke earned schedule, against a planned-value baseline
earned_schedulethe earned schedule for a given earned value

Chart tools return a PNG image the client can display.

ToolPurpose
gantt_charta Gantt chart of the schedule, critical path highlighted
network_chartthe activity network with the critical path
evm_chartthe earned value S-curve (PV/EV/AC + forecast)
criticality_chartMonte Carlo per-activity criticality bars
completion_histogramMonte Carlo completion-time histogram

Installation

pip install pmcontrols-mcp

Or run it without installing, with uv:

uvx pmcontrols-mcp

Configuration

Add the server to your MCP client's configuration:

{
  "mcpServers": {
    "pmcontrols": {
      "command": "pmcontrols-mcp"
    }
  }
}

The server communicates over stdio and works with any MCP-compatible client.

Example

Calling critical_path with a list of activities returns a structured result the agent reads directly, instead of computing the schedule itself:

{
  "method": "cpm",
  "stats": {"project_duration": 15.0, "n_activities": 8.0, "n_critical": 5.0},
  "meta": {
    "critical_activities": ["A", "C", "E", "G", "H"],
    "version": "0.2.1",
    "input_hash": "sha256:...",
    "computed_at": "2026-06-15T09:14:02+00:00"
  },
  "table": {"activity": ["A", "B", "..."], "slack": [0.0, 1.0, "..."]}
}

Every result carries provenance (library version, input hash, timestamp), so a figure an agent reports can be recomputed and audited later.

Design

The reasoning behind routing project-control arithmetic through a validated tool, rather than letting a model generate it, is set out in Project control is not a language task.

Related

pmcontrols is the underlying library this server wraps.

License

MIT. Written and maintained by Atakan Arikan, MSc Student at Tsinghua University and Politecnico di Milano.

Ver o original no GitHub

Bom para

Relacionados