Glob.AI Hubs Orchestrator MCP Server
Globant publishes an MCP server card at https://glob.ai/.well-known/mcp/server-card.json describing an MCP server named "orchestrator" that exposes the Glob.AI Hubs Orchestrator API — projects, goals, plans, work items, runs, artifacts and inbox — to Claude Code, Globant CODA and other MCP-compatible agents. The card and the provider's own published agent skill both state plainly that this is a LOCAL STDIO server and that no hosted HTTP/SSE MCP endpoint exists today.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport
Tools
list_projects— List projects with optional filtersget_project— Get a project by idlist_goals— List goalsget_goal— Get a goal by idupdate_goal_status— Update a goal's statuslist_goal_plans— List plans under a goalget_plan— Get a plan by idget_plan_work_items— List work items for a planstart_run— Start execution of a planget_work_item— Get a work item by idupdate_work_item_status— Report progress on a work itemget_run— Get a run by idget_run_status— Get run statusupdate_run_status— Update run statuscreate_artifact— Create an artifact on a runlist_run_artifacts— List artifacts for a runget_artifact— Get an artifact by idget_artifact_status— Get artifact statusupdate_artifact— Update an artifactlist_project_aipods— List AI pods for a projectregister_run_agent— Register an agent participating in a runlist_run_agents— List agents on a runupdate_run_agent— Update a run agentcreate_external_plan— Create an external plancreate_job— Create a jobget_job— Get a job by idget_plan_content— Get plan contentupdate_plan_content— Update plan contentget_artifact_content— Get artifact contentlist_inbox_items— List inbox itemsget_inbox_item— Get an inbox itemmark_inbox_item_read— Mark an inbox item readget_inbox_unread_count— Get inbox unread count
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.