convez.ai
MCP ServerIntegração & APIsIntermediário
orchestra-hq

Orchestra MCP Server

orchestra-hq/orchestra-mcp

Integração MCP para gerenciar pipelines e execuções no Orchestra

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP para a plataforma Orchestra, fornecendo acesso programático a pipelines, execuções e observabilidade. Permite validar, criar, atualizar e executar pipelines, além de consultar logs e artefatos através da API do Orchestra.

Instalação

$npx convez-ai orchestra-hq/orchestra-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
1
Acompanhando
0
Saúde
25%
Último commit
há 1 dia
Versão
2026.11.16-0
Issues abertas
0
Contribuidores
4

Casos de uso

  • Automatizar criação e execução de pipelines de dados
  • Monitorar status de execuções e acessar logs em tempo real
  • Integrar orquestração de workflows em assistentes IA
  • Validar definições de pipeline antes do deploy
  • Consultar linhagem de dados e artefatos de execução

Veredito

MCP server bem estruturado e maduro para integração com Orchestra. Cobertura completa de operações de pipeline lifecycle, execução e observabilidade, com suporte a autenticação via API key e endpoints hospedados. Ideal para quem já usa Orchestra e busca automação via Claude.

README

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

Orchestra MCP Server

A Model Context Protocol (MCP) server for the Orchestra API. End users can connect directly to Orchestra's hosted MCP endpoint and authenticate with their Orchestra API key.

Quick Start

Use Orchestra's hosted MCP endpoint:

  • URL: https://mcp.getorchestra.io/orchestra
  • Required header: Authorization: Bearer <YOUR_ORCHESTRA_API_KEY>
  • API key location: Orchestra workspace settings

Available Tools

ToolAuth requiredPurposeCategory
validate_pipelineNoCheck a pipeline definition (JSON object) against the Orchestra schema (POST /pipelines/schema). Does not persist anything.Pipeline lifecycle
list_pipelinesYesList all pipelines for the workspace with latest run metadata (GET /pipelines).Pipeline lifecycle
get_pipelineYesFetch a single pipeline by selector (GET /pipeline).Pipeline lifecycle
create_pipelineYesCreate an Orchestra-backed pipeline from a definition object (POST /pipelines).Pipeline lifecycle
update_pipelineYesUpdate an Orchestra-backed pipeline by alias (PUT /pipelines/{alias}). Git-backed pipelines cannot be updated here.Pipeline lifecycle
migrate_pipelineYesMigrate an Orchestra-backed pipeline to git-backed storage (PATCH /pipelines/storage-settings). The YAML must already exist in the repo.Pipeline lifecycle
delete_pipelineYesDisabled by default. Delete a pipeline by selector (DELETE /pipelines). Set ORCHESTRA_ENABLE_DELETE to expose it.Pipeline lifecycle
import_pipelineYesImport a pipeline whose YAML lives in a Git repository (POST /pipelines/import).Pipeline lifecycle
start_pipelineYesStart a run by alias or pipeline ID (POST /pipelines/{alias_or_id}/start). Optionally target a version_number.Pipeline running
get_pipeline_run_statusYesPoll a single pipeline run’s status.Pipeline running
cancel_pipeline_runYesRequest cancellation of a pipeline run.Pipeline running
get_pipeline_run_lineage_urlNoReturn the UI URL for a pipeline run’s lineage graph (derived from ORCHESTRA_ENV).Pipeline running
list_pipeline_runsYesList runs with optional time range plus comma-separated status and ID filters.Observability
list_task_runsYesList task runs with optional comma-separated filters (including integration).Observability
list_operationsYesList operations with optional comma-separated filters.Observability
list_assetsYesList data assets with optional comma-separated type and integration filters.Observability
list_task_run_logsYesList log filenames for a task run.Logs and artifacts
download_task_run_logYesDownload a log file (optional HTTP Range); content is base64-encoded in the result.Logs and artifacts
list_task_run_artifactsYesList artifact filenames for a task run.Logs and artifacts
download_task_run_artifactYesDownload an artifact file; content is base64-encoded in the result.Logs and artifacts

Cursor

Add this to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "orchestra": {
      "url": "https://mcp.getorchestra.io/orchestra",
      "headers": {
        "Authorization": "Bearer <YOUR_ORCHESTRA_API_KEY>"
      }
    }
  }
}

Claude Code

Add the hosted server with:

claude mcp add --transport http --header "Authorization: Bearer <YOUR_ORCHESTRA_API_KEY>" orchestra https://mcp.getorchestra.io/orchestra

Other MCP clients

Any MCP client that supports remote HTTP/SSE servers can connect with this shape:

{
  "mcpServers": {
    "orchestra": {
      "url": "https://mcp.getorchestra.io/orchestra",
      "headers": {
        "Authorization": "Bearer <YOUR_ORCHESTRA_API_KEY>"
      }
    }
  }
}

Managing Multiple Workspaces

If you need to connect to multiple Orchestra workspaces, you can set up separate MCP server connections with workspace-specific API keys:

{
  "mcpServers": {
    "orchestra-data-quality-tests": {
      "url": "https://mcp.getorchestra.io/orchestra",
      "headers": {
        "Authorization": "Bearer <DATA_QUALITY_WORKSPACE_API_KEY>"
      }
    },
    "orchestra-sales-integrations": {
      "url": "https://mcp.getorchestra.io/orchestra",
      "headers": {
        "Authorization": "Bearer <SALES_WORKSPACE_API_KEY>"
      }
    }
  }
}

Run Locally

This section discusses how to run the MCP server locally, and is mainly intended for contributors.

Prerequisites

  • Python 3.10 or higher
  • uv package manager
  • Orchestra API key

Install dependencies

# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install project dependencies
uv sync

Set API key

export ORCHESTRA_API_KEY="your-orchestra-api-key"

(Optional) Select environment for local runs

For local development, the server defaults to app. You can override it with ORCHESTRA_ENV:

export ORCHESTRA_ENV="dev"

Valid values:

  • app (default)
  • stage
  • dev

(Optional) Enable destructive pipeline deletion

By default, the MCP delete_pipeline tool is not registered to avoid accidental destructive actions. To expose it, set ORCHESTRA_ENABLE_DELETE before starting the server:

export ORCHESTRA_ENABLE_DELETE="true"

Only the following values are recognized:

  • "true"
  • "TRUE"
  • "1"

Run the server

python -m orchestramcp.server

Or with FastMCP CLI:

uv run fastmcp run orchestramcp/server.py

Development

  • Run uv run pytest to run tests.
  • Run uv run ruff check . and uv run ruff format . to check and format code.

PRs to main will trigger CI checks in GitHub, main branch merges release to the dev & stage environments, and Github releases relase to the production environment.

Ver o original no GitHub

Bom para

Relacionados