$ loading_
Manage Globus data transfers and compute tasks through AI-driven automation.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "globus-mcp" yet — see the docs or source repo.
Use Globus to sync /project/raw-data/ from endpoint A to /archive/raw-data/ on endpoint B, preserve the directory structure, and return the task ID plus how to check status after creation.
Returns the created Globus transfer task details, including source and destination paths, task ID, and status-check instructions.
Check the current status of Globus task 7f3c-example-task-id. If it failed, summarize the error cause; if it is still running, describe progress and suggest next steps.
Outputs task status, progress or failure reason, and provides recommendations for troubleshooting or waiting for completion.
Start a data preprocessing job on a Globus-connected compute resource, using /data/input as input and /data/output as output, and report the submission result and tracking details.
Returns the compute job submission result, relevant task identifiers, and information for tracking or checking execution status later.
Transfer data and run remote compute jobs across HPC endpoints with Globus.
Manage MCP server configurations with listing, toggling, and version control.
Aggregate multiple MCP servers into a few fixed tools for AI apps.
Manage GitHub repositories, labels, topics, and files through API automation.
Manage local semantic dataspaces, ingest documents, and run semantic search via MCP.
Manage GitHub repositories, pull requests, issues, and workflows with natural language.