Skip to main content
Glama

Engineering MCP

Local MCP for engineering: tickets, QA evidence, and time go in; investigation closes root cause; knowledge stays; reporting comes out ready.

It doesn't replace what you already have:

MCP

Role

engineering-mcp (this)

Engineering OS — work + evidence + time + RCA + memory + report

qa-lab-agent

Runs tests, generates spec, self-corrects

qa-oracle

CI / LambdaTest / historical Jira logs

ENGINEERING MCP
      │
      ├── WORK        tickets · tasks · projects
      ├── QA          testing evidence · bugs · artifacts
      └── TIME        tracking · estimates · metrics
              │
              ▼
        INVESTIGATION
              │
              ▼
          KNOWLEDGE
              │
              ▼
          REPORTING

Problem it solves

A Jira ticket, a CI failure, and a time entry live in three places. When status time comes, no one puts the package together.

This MCP records the cycle in the same local database:

  1. Opens the ticket (WORK)

  2. Attaches the fail / bug / screenshot (QA) — without running the suite

  3. Logs hours and estimate (TIME)

  4. Investigates to root cause (INVESTIGATION)

  5. Becomes a playbook (KNOWLEDGE)

  6. report_ticket returns the package for handoff, daily, or career evidence


Related MCP server: MCP Project Bridge

Requirements

  • Node 22+ (native node:sqlite, same as qa-oracle)

  • MCP client (Cursor)


Installation (no absolute path)

Cursor does not point to the Desktop folder. It downloads the package — same as qa-lab-agent. The database lives in ~/.engineering-mcp/engineering.db, on any machine.

Config in Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "engineering": {
      "command": "npx",
      "args": ["-y", "engineering-mcp"]
    }
  }
}

No args with /Users/.... No ENGINEERING_MCP_DB. Reload the MCPs.

This works after the package is on npm or GitHub (below). Until publishing, use the local shortcut (also without a path in mcp.json):

cd ~/Desktop/engineering-mcp
npm install
npm install -g .
{
  "mcpServers": {
    "engineering": {
      "command": "engineering-mcp"
    }
  }
}

npm install -g . puts the command on the PATH. The mcp.json only mentions the name.


Where to host (npm vs GitHub vs cloud)

Where

What goes to the cloud

Config in Cursor

npm (recommended)

Only the code, public

"command": "npx", "args": ["-y", "engineering-mcp"]

GitHub

Only the code, public

"args": ["-y", "github:Wesley-Gomes93/engineering-mcp"]

HTTP server

Code and your tickets

"url": "https://your-domain/mcp"

No need for your own site. The “site” is npmjs.com — the same as mcp-lab-agent. Cursor runs the MCP on your machine; the cloud only delivers the code.

Cloud like URL ("url": "https://...") exists in Cursor, but then SQLite is no longer local: tickets, bugs, and hours would live on a server. That's a multi-user product, not this v0.

Publishing to npm (same as lab-agent)

The name engineering-mcp is free. With an npm account already logged in:

cd ~/Desktop/engineering-mcp
npm test
npm publish --access public

After that, any Mac just uses the npx block above.

Publishing to GitHub (without npm)

cd ~/Desktop/engineering-mcp
git init
git add .
git commit -m "feat: engineering mcp v0.1"
gh repo create Wesley-Gomes93/engineering-mcp --public --source . --remote origin --push

Alternative config, still without a path:

{
  "mcpServers": {
    "engineering": {
      "command": "npx",
      "args": ["-y", "github:Wesley-Gomes93/engineering-mcp"]
    }
  }
}

Restart Cursor (or reload the MCPs). The database is created on its own in ~/.engineering-mcp/.


Typical loop

"Abre um projeto Atlas (ATL) e um bug P1: timeout no checkout"
  → work_upsert_project + work_upsert_ticket

"Registra o fail do checkout.spec.js e anexa o log"
  → qa_record_run + qa_attach_evidence

"Estima 4h e lança 1.5h de repro"
  → time_estimate + time_log

"Abre investigação: hipótese de seletor instável"
  → investigate_open + investigate_add_finding

"Fecha como flaky: timing no botão Finalizar"
  → investigate_conclude

"Vira playbook: wait da animação + data-testid"
  → knowledge_save

"Me dá o pacote do ticket"
  → report_ticket

If you don't know the tool: eng_route with the phrase in Portuguese.


Tools

WORK

Tool

Does

work_upsert_project

Creates/updates project (key becomes prefix: ATL-1)

work_list_projects

Lists projects

work_upsert_ticket

Creates/updates ticket (story/bug/task/spike/epic)

work_upsert_task

Child task

work_list

Filter by project, status, type, text

work_board

Kanban: backlog → todo → doing → review → done

work_get

Detail + tasks

Status: backlog · todo · doing · review · done
Priority: p0 … p3
external_key stores the Jira/GitLab key without pulling an API yet.

QA

Tool

Does

qa_record_run

Run evidence (pass/fail/flaky/blocked)

qa_record_bug

Local bug + classification

qa_attach_evidence

log / screenshot / report / url

qa_list

Runs + bugs + evidence for the ticket

Running tests still happens in qa-lab-agent. Corporate Jira history stays in qa-oracle.

TIME

Tool

Does

time_estimate

Estimated hours on the ticket

time_log

Actual hours

time_metrics

Estimated vs actual vs remaining

INVESTIGATION

Tool

Does

investigate_open

Opens RCA (ticket and/or bug)

investigate_add_finding

observation / evidence / hypothesis / decision

investigate_conclude

Root cause + classification

investigate_list

Open or concluded

Classification: bug · flaky · infra · regression · unknown

KNOWLEDGE

Tool

Does

knowledge_save

Playbook / lesson / pattern

knowledge_search

FTS5 search ("have we seen this?")

REPORTING

Tool

Does

report_ticket

Full package for a ticket

report_status

Project snapshot (N days)

eng_route

Which domain to use


Structure

engineering-mcp/
├── src/
│   ├── server.js              # MCP stdio
│   ├── lib/store.js           # SQLite — fonte da verdade
│   └── domains/
│       ├── work.js
│       ├── qa.js
│       ├── time.js
│       ├── investigation.js
│       ├── knowledge.js
│       └── reporting.js
└── test/store.test.js

Default database: ~/.engineering-mcp/engineering.db (doesn't travel with the repo).

Nothing leaves the machine beyond what the agent already sees in the chat. No Jira/GitLab in v0 — external_key is the hook for sync later.


v0 vs later

Now: local database, closed loop, Cursor.

Later (only if v0 is used):

  • Jira → ticket sync (reuse qa-oracle client)

  • Import run from qa-lab-agent / GitLab job

  • HTML dashboard from report_status


Security

  • Database in ~/.engineering-mcp/ (outside the repo)

  • No tokens in v0

  • Publishing to npm/GitHub sends code, not tickets

Available Tools

23 tools
eng_routeRoteador de domínioA

Encaminha uma tarefa em linguagem natural para o domínio certo: work, qa, time, investigation, knowledge ou reporting.

Inputs: task (required).

investigate_add_findingAdicionar findingC

INVESTIGATION: adiciona observação, evidência, hipótese ou decisão a uma investigação aberta.

Inputs: body (required), investigation_id (required), kind.

investigate_concludeConcluir investigaçãoB

INVESTIGATION: fecha com causa raiz e classificação (bug/flaky/infra/regression). Depois grave knowledge.

Inputs: investigation_id (required), hypothesis, root_cause, classification.

investigate_listListar investigaçõesC

INVESTIGATION: lista investigações, opcionalmente por ticket ou status.

Inputs: status, ticket_id.

investigate_openAbrir investigaçãoB

INVESTIGATION: abre uma investigação (RCA) ligada a ticket e/ou bug. Cruza WORK + QA. Para logs CI/Jira use também qa-oracle.

Inputs: title (required), bug_id, ticket_id, hypothesis.

knowledge_saveSalvar conhecimentoB

KNOWLEDGE: grava playbook, lição ou padrão a partir de uma investigação. Memória local (FTS).

Inputs: body (required), title (required), kind, tags, +2 more.

qa_attach_evidenceAnexar evidênciaC

QA: anexa log, screenshot, report ou URL a um ticket, bug ou run.

Inputs: path_or_url (required), kind, note, bug_id, +2 more.

qa_listListar QA de um ticketA

QA: lista runs, bugs e evidências. Filtra por ticket_id se informado.

Inputs: ticket_id.

qa_record_bugRegistrar bugA

QA: grava um bug local (severity + classificação). Para histórico Jira corporativo use o MCP qa-oracle (search_bug_history).

Inputs: title (required), status, severity, ticket_id, +2 more.

qa_record_runRegistrar evidência de testeA

QA: grava um run de teste (pass/fail/flaky/blocked) ligado a um ticket. Não executa testes — para rodar, use o MCP qa-lab-agent.

Inputs: status (required), suite, source, summary, +1 more.

report_statusStatus reportB

REPORTING: snapshot do projeto — board counts, tempo, falhas recentes, bugs e investigações abertas.

Inputs: days, project_id, project_key.

report_ticketPacote completo do ticketB

REPORTING: junta WORK + QA + TIME + INVESTIGATION + KNOWLEDGE de um ticket. Use para status, handoff ou evidência.

Inputs: ticket_id (required).

time_estimateDefinir estimativaC

TIME: grava ou atualiza a estimativa em horas de um ticket.

Inputs: hours (required), ticket_id (required), note.

time_logLançar horasD

TIME: lança tempo trabalhado em um ticket ou task.

Inputs: hours (required), note, task_id, logged_at, +1 more.

time_metricsMétricas de tempoC

TIME: estimado vs real vs restante, por ticket, projeto ou global.

Inputs: ticket_id, project_id, project_key.

work_boardBoard kanbanC

WORK: visão kanban (backlog/todo/doing/review/done) de um projeto.

Inputs: project_id, project_key.

work_getDetalhe do ticketA

WORK: detalhe de um ticket com tasks. Para pacote completo (QA+tempo+investigação) use report_ticket.

Inputs: id (required).

work_listListar ticketsC

WORK: lista tickets com filtro por projeto, status, tipo ou texto.

Inputs: type, query, status, project_id, +1 more.

work_list_projectsListar projetosC

WORK: lista projetos locais do Engineering MCP.

Inputs: status.

work_upsert_projectCriar ou atualizar projetoB

WORK: cria ou atualiza um projeto de engenharia (ex: app, backend, QA lab). Use antes de abrir tickets.

Inputs: id, key, name, status, +1 more.

work_upsert_taskCriar ou atualizar taskC

WORK: cria/atualiza uma task filha de um ticket.

Inputs: id, title, status, ticket_id.

work_upsert_ticketCriar ou atualizar ticketB

WORK: cria/atualiza ticket (story, bug, task, spike, epic). IDs no formato KEY-N (ex: ENG-3). Passe id para atualizar status.

Inputs: id, type, title, status, +5 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 23 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action (e.g., work_upsert_project vs work_upsert_ticket vs work_upsert_task). Lifecycle tools like investigate_open/add_finding/conclude and qa_record_run/record_bug are clearly separate, and the reporting and knowledge tools have unique roles. No two tools appear to do the same thing.

    Naming Consistency4/5

    The naming pattern is generally domain_prefix + verb_noun (e.g., work_upsert_ticket, qa_record_run). Minor deviations include 'work_list' lacking an explicit object, 'work_board' and 'time_metrics' using nouns as commands, and 'eng_route' not following the domain-prefix structure. Overall, it's predictable and readable.

    Tool Count4/5

    With 23 tools, the server is on the heavier side, but the count is justified by the breadth of domains covered (work, time, investigation, knowledge, QA, reporting, routing). Each tool serves a specific purpose, and the volume aligns with the comprehensive engineering management scope.

    Completeness4/5

    The tool surface covers the full lifecycle for tickets, tasks, projects, investigations, time tracking, and QA evidence, including reporting and knowledge handoff. Minor gaps include the absence of explicit delete or archive operations on tickets/projects, and no bulk actions, but these are not critical for typical workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables recording, querying, and summarizing daily work entries with tags using a local SQLite database. Supports work logging, search, timeline queries, tag management, and automated reminders for tracking daily tasks.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables multi-project workspaces to share structured notes, API contracts, and handoff messages via a local SQLite database, with versioning and read tracking.
      GPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables developers to maintain a local engineering journal, log work manually or from git history, and let AI assistants query, summarize, and draft standup updates, changelogs, and retro notes.
      MIT