ワンクリックで
galaxy-mcp-reference
Galaxy MCP server tools reference for histories, datasets, tools, and workflows
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Galaxy MCP server tools reference for histories, datasets, tools, and workflows
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when authoring a Galaxy User-Defined Tool (UDT) -- a `class: GalaxyUserTool` YAML definition that wraps a container and command into a tool a non-admin user creates and runs (e.g. via Galaxy MCP create_user_tool / run_user_tool, or POST /api/unprivileged_tools). Not for classic XML/ToolShed tool wrappers.
Use this skill when asked to create, draft, or write a Galaxy workflow report template for the Workflow Editor's Report tab. Triggers on requests like "create a report for this workflow", "draft a workflow report template", "write a Galaxy report for workflow <id/url>".
Galaxy Collection Transformation Command - transform Galaxy dataset collections reproducibly using Galaxy's native tools. Use when asked to filter, sort, relabel, restructure, flatten, nest, merge, or otherwise manipulate Galaxy collections.
Router for Galaxy MCP, JupyterLite notebooks, and BioBlend automation
Building UCSC Track Hubs (track hubs and assembly hubs) — bigBed/bigChain/bigMaf format requirements, composite-track rules, hub.txt / genomes.txt / trackDb.txt structure. Use when emitting a UCSC hub from Galaxy outputs, wrapping a hub-publishing tool, or debugging hubCheck failures.
Galaxy tool development reference — creating new tools, testing, IUC review preparation, and updating existing tools. Use when authoring or modifying Galaxy tool wrappers for tools-iuc.
| name | galaxy-mcp-reference |
| description | Galaxy MCP server tools reference for histories, datasets, tools, and workflows |
| metadata | {"surfaces":["loom"]} |
| when_to_use | Reach for this before any Galaxy MCP tool call -- creating/listing histories, uploading data, finding and running tools, inspecting datasets or invocations -- and for the common gotchas (id vs name, history vs dataset ids, collection shapes). |
| user_invocable | true |
Complete reference for Galaxy MCP server functions.
mcp__galaxy__connect(url, api_key) # Connect to Galaxy instance
mcp__galaxy__get_server_info() # Server version and config
mcp__galaxy__get_user() # Current user details
mcp__galaxy__list_history_ids() # Quick list: {id, name}
mcp__galaxy__get_histories(limit, offset, name) # Paginated, filterable
mcp__galaxy__get_history_details(history_id) # Metadata only, no datasets
mcp__galaxy__get_history_contents(history_id, limit, offset, order) # Datasets
mcp__galaxy__create_history(history_name) # Create new history
mcp__galaxy__get_dataset_details(dataset_id, include_preview, preview_lines)
mcp__galaxy__download_dataset(dataset_id, file_path) # Omit file_path for memory
mcp__galaxy__upload_file(path, history_id)
mcp__galaxy__upload_file_from_url(url, history_id, file_type, dbkey)
mcp__galaxy__get_job_details(dataset_id) # Job that created this dataset
mcp__galaxy__search_tools_by_name(query)
mcp__galaxy__search_tools_by_keywords(keywords) # keywords is a list
mcp__galaxy__get_tool_details(tool_id, io_details)
mcp__galaxy__get_tool_run_examples(tool_id) # XML test cases
mcp__galaxy__get_tool_citations(tool_id)
mcp__galaxy__get_tool_panel() # Full toolbox hierarchy
mcp__galaxy__run_tool(history_id, tool_id, inputs)
mcp__galaxy__list_workflows(workflow_id, name, published)
mcp__galaxy__get_workflow_details(workflow_id, version)
mcp__galaxy__invoke_workflow(workflow_id, inputs, params, history_id)
mcp__galaxy__get_invocations(invocation_id, workflow_id, history_id)
mcp__galaxy__cancel_workflow_invocation(invocation_id)
mcp__galaxy__get_iwc_workflows() # Full manifest
mcp__galaxy__search_iwc_workflows(query) # Search by name/description/tags
mcp__galaxy__import_workflow_from_iwc(trs_id)
# Find candidate tools
search_tools_by_name(query="hyphy")
# Inspect I/O
get_tool_details(tool_id="toolshed.g2.bx.psu.edu/repos/iuc/hyphy_fel/hyphy_fel/2.5.84+galaxy0", io_details=True)
# 1. Create history
create_history(history_name="Test: My Workflow")
# 2. Upload or reuse datasets
upload_file(path="/path/to/data.txt", history_id="...")
# 3. Invoke workflow
invoke_workflow(workflow_id="...", inputs={"0": {"id": "DATASET_ID", "src": "hda"}}, history_id="...")
# 4. Inspect outputs
get_history_contents(history_id="...", order="create_time-dsc")
# 5. Fix and repeat
# Page 1 (newest first)
get_history_contents(history_id="...", limit=100, offset=0, order="hid-dsc")
# Page 2
get_history_contents(history_id="...", limit=100, offset=100, order="hid-dsc")
hid-asc - oldest first (default)hid-dsc - newest firstcreate_time-dsc - most recently createdupdate_time-dsc - most recently modifiedname-asc - alphabeticalhistory-access.md - Detailed history/dataset access patternsgotchas.md - Common pitfalls and solutions