convez.ai
MCP ServerIntegração & APIsIntermediário
Uluops

UluOps Ops MCP

Uluops/-uluops-ops-mcp

MCP server para operações inteligentes e gestão de validações na plataforma UluOps

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que conecta Claude, Cursor e outros hosts ao UluOps Platform API, fornecendo 48 ferramentas para rastreamento de validações, analytics e gestão de problemas. Segue padrão thin client: toda lógica de negócio fica no backend, o servidor foca apenas em tradução de protocolos.

Instalação

$npx convez-ai Uluops/-uluops-ops-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
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 2 semanas
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Integrar Claude Code e Cursor com plataforma UluOps para automação operacional
  • Rastrear validações e analytics de forma programática via MCP
  • Gerenciar issues e operações através de agentes de IA conectados ao backend UluOps

Veredito

MCP server maduro e bem estruturado para integração com UluOps Platform. Documentação clara, suporta npx sem instalação, e mantém arquitetura limpa (thin client). Ideal para times que usam Claude/Cursor e precisam orquestrar operações na plataforma UluOps.

README

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

UluOps · Operating Intelligence as Infrastructure


@uluops/ops-mcp

npm version License: MIT Node.js Version TypeScript Tests

MCP (Model Context Protocol) server for the UluOps Platform API. Provides 48 tools and 3 resources (2 functional, 1 template placeholder) that enable Claude Code, Cursor, and other MCP hosts to interact with the UluOps Platform.

Design Philosophy

Thin Client Pattern: This MCP server contains zero business logic. All data processing, validation, storage, and analytics are handled by the backend API. The server's sole responsibility is protocol translation between MCP's stdio-based JSON-RPC and the backend's REST API.

Installation

Requires Node.js 18 or later.

Option A — npx (no install):

npx -y @uluops/ops-mcp

Option B — global install:

npm install -g @uluops/ops-mcp

This exposes the uluops-ops-mcp binary on your PATH.

Configuration

Set environment variables in your MCP host configuration (see "Usage with Claude Code" below) or in a .env file when developing locally.

VariableDescriptionRequired
ULUOPS_API_KEYAPI authentication key (must start with ulr_, min 20 chars)Yes
ULUOPS_ORG_SLUGOrganization slug for multi-org contextsNo
ULUOPS_TRACKER_TIMEOUTRequest timeout (ms)No (default: 30000)
ULUOPS_TRACKER_RETRIESNumber of retry attempts on failureNo (default: 3)
LOG_LEVELLogging level (debug, info, warn, error)No (default: info)

The backend URL is handled automatically by @uluops/ops-sdk — production by default, no configuration needed.

Advanced Logging

By default this server logs only to stderr at info level. To enable structured file logging, set:

VariableDescriptionDefault
ENABLE_FILE_LOGGINGWrite JSON logs to diskfalse
LOG_DIRDirectory for log fileslogs
VERBOSE_LOGGINGInclude extra diagnostic detailfalse
LOG_PERFORMANCE_METRICSEmit per-call timing metricsfalse

When ENABLE_FILE_LOGGING=true, a logs/ directory is created in the process's working directory.

Production Tightening

VariableDescriptionDefault
ENABLE_DETAILED_ERRORSPropagate redacted error reasons in error.message so callers can diagnose failures without parsing the data envelope. Set to false to suppress in tightened production deployments.true

Usage with Claude Code

Add to your Claude Code MCP configuration (.mcp.json):

Option 1: npx (lowest friction — no install)

{
  "mcpServers": {
    "uluops-ops": {
      "command": "npx",
      "args": ["-y", "@uluops/ops-mcp"],
      "env": {
        "ULUOPS_API_KEY": "ulr_your-api-key-here"
      }
    }
  }
}

Option 2: Globally installed binary

{
  "mcpServers": {
    "uluops-ops": {
      "command": "uluops-ops-mcp",
      "args": [],
      "env": {
        "ULUOPS_API_KEY": "ulr_your-api-key-here"
      }
    }
  }
}

Quick Start Examples

Once configured, Claude Code can use the uluops tracker tools:

// Save validation results from a workflow run
save_run({
  project: "my-project",
  workflow_type: "ship",
  agents: [{ name: "code-validator", score: 85, decision: "PASS" }],
  recommendations: [{ agent: "code-validator", title: "Fix lint error", priority: "suggested" }]
})

// Query open issues for a project
query_issues({ project: "my-project", status: "open", priority: "critical" })

// Get project summary with issue counts and trends
get_project_summary({ project: "my-project" })

Rate Limiting Configuration

This server uses mcp-secure-server with configuration optimized for Claude Code's usage patterns.

Claude Code Usage Patterns

OperationTypical Parallel CallsNotes
Query context (summary, issues, runs)3-5Low burst
Create issues from validation workflow10-30High burst
Update agents with metrics6Medium burst
Save recommendations1 (with array)Single call

Claude Code issues tool calls in short, intense bursts (<2s) followed by "thinking" pauses. The default configuration accounts for this:

{
  securityLevel: 'basic',
  maxRequestsPerMinute: 120,
  burstThreshold: 15,        // Covers 90% of parallel operations
  burstWindowMs: 5000,       // 5s window resets between thinking periods
  automationDetection: {
    enabled: false,          // Claude Code is trusted automation
  },
}

Why These Settings

  • burstThreshold: 15 - Handles typical validation workflow bursts (10-15 parallel issue creates or queries)
  • burstWindowMs: 5000 - Short window resets between Claude's "thinking" periods, preventing false positives
  • automationDetection: disabled - Claude Code IS automation with consistent timing patterns; detecting it as a "bot" would block legitimate use

Available Tools

Core Tools (P0)

ToolDescription
save_runSave validation pipeline output with issue correlation
query_issuesQuery issues with filtering by status, priority, validator
update_statusUpdate issue status (completed, deferred, wontfix)
get_project_summaryGet project overview with workflow and validator stats
delete_projectDelete project data (requires confirmation)

Extended Tools (P1)

ToolDescription
create_issueCreate a user-submitted issue directly (outside validation runs)
get_issue_detailsFull issue lifecycle with occurrences, notes, history
get_run_detailsRun information with all recommendations and stats
diff_runsCompare two validation runs (fixed, new, unchanged issues)
archive_runsArchive old runs without deletion
get_analyticsCross-project analytics (8 metric types; cross_project_patterns returns [] — placeholder until pattern aggregation ships)
search_issuesSearch issues across projects with relevance ranking
list_agentsList canonical agents from manifest
validate_runPreview save operation without modifying database
get_issue_historyMerged audit-event stream (occurrences, status, notes) as an envelope {issueId, events[], totalEvents, truncated} — includes undo tombstones (v0.4.0+)
add_issue_noteAdd context, resolution, or blocker notes to issues
edit_issueEdit issue metadata (title, file_path, severity, etc.)
merge_issuesMerge duplicate issues into a target issue
bulk_update_statusBulk update multiple issue statuses in one transaction
update_runUpdate run metadata post-hoc (tokens, scores, timestamps)
get_agent_reliabilityAnalyze agent effectiveness and reliability scores
get_agent_lifecycleLifecycle metrics for an agent across runs

Project Tools (P2)

ToolDescription
list_projectsList all active projects
get_projectGet a single project by ID or name
get_project_trendsGet issue trends over time for a project
create_projectCreate a new project
update_projectUpdate a project name
soft_delete_projectSoft delete a project (can be restored later)
restore_projectRestore a soft-deleted project

Run Tools (P2)

ToolDescription
get_runGet a run by UUID
list_runsList runs for a project
get_latest_runGet the latest run for a project
delete_runDelete a run (requires confirmation)

Issue Tools (P2)

ToolDescription
get_issue_by_fingerprintGet an issue by its SHA-256 fingerprint
update_issue_by_fingerprintUpdate an issue status by its fingerprint
restore_issueRestore a soft-deleted issue
soft_delete_issueSoft delete an issue (can be restored later)
undo_issue_statusUndo the last status change on an issue

Taxonomy Tools (P2)

ToolDescription
get_taxonomyGet the failure taxonomy schema (domains, modes, severities)
get_full_taxonomy_analyticsGet full taxonomy analytics with distribution by domain
get_burndownGet taxonomy burndown with time series and trend analysis per failure domain
get_velocityGet velocity metrics per failure mode with sparkline data and trend reliability
get_discoveryGet discovery timeline showing new vs recurring issues over time
get_agent_matrixGet agent-taxonomy coverage matrix with blind spot detection

Analysis Tools (P2)

ToolDescription
get_run_analysisStructured analysis records for a single run (decision, scoring, findings)
get_project_analysisAggregated analysis records across all runs in a project
query_analysis_recordsQuery analysis records by type, classification, severity
get_agent_runs_analysisPer-run analysis records grouped by agent

Available Resources

MCP resources provide read-only access to validation data via the validation:// URI scheme.

ResourceURIDescription
Projectsvalidation://projectsList all tracked projects
Project Summaryvalidation://projects/{project}Template placeholder (use get_project_summary tool)
Taxonomyvalidation://taxonomyFailure taxonomy schema for classifying issues

Resource Usage

// List all projects (returns JSON array of project names)
read_resource("validation://projects")

// Get the failure taxonomy schema (domains, modes, severity codes)
read_resource("validation://taxonomy")

Note: For project-specific data, use the get_project_summary tool instead of resources. MCP resource templates with parameters are not fully supported by the SDK.

Development

# Install dependencies
npm install

# Development mode with watch
npm run dev

# Run tests
npm test

# Type checking
npm run typecheck

# Linting
npm run lint

# Build for production
npm run build

License

MIT

Ver o original no GitHub

Bom para

Relacionados