Bio-OS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | Yes | Path to the bioos-mcp-server/src directory | |
| MIRACLE_ACCESS_KEY | Yes | Your Miracle Cloud access key | |
| MIRACLE_SECRET_KEY | Yes | Your Miracle Cloud secret key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| validate_wdlB | 验证 WDL 文件的语法正确性 |
| list_workspaceC | 列出当前登录环境的工作空间名称与描述 |
| import_workflowC | 该工具用于将 WDL 工作流上传到 Bio‑OS,支持上传单个文件或整个目录。 |
| generate_inputs_json_template_bioosC | Bio-OS 上已导入 workflow 的 inputs.json 查询,并生成符合的输入参数模板 |
| compose_input_jsonC | 根据用户给的数值生成input.json |
| validate_workflow_input_jsonC | 验证工作流输入 JSON 文件 |
| submit_workflowC | 提交并监控 Bio-OS 工作流 |
| check_workflow_run_statusC | 查询工作流运行状态 |
| check_workflow_import_statusC | 查询工作流导入状态 |
| get_workflow_logsD | 获取工作流执行日志 |
| delete_submissionC | Bio-OS 删除工作流提交 |
| create_workspace_bioosC | Bio-OS 创建新工作空间 |
| export_bioos_workspaceD | Bio-OS 导出工作空间元信息 |
| create_iesappC | 在指定的workspace中新建一个 IES 实例,用户可在该 IES 实例上进行分析 |
| check_ies_statusC | 查看指定workspace中的指定IES 实例的创建状态 |
| get_ies_eventsB | 查看指定workspace中的指定IES实例的创建日志 |
| upload_dashboard_fileB | 上传__dashboard__.md文件到指定工作空间的S3桶 |
| search_dockstoreD | 在Dockstore中检索工作流 |
| fetch_wdl_from_dockstoreC | 从Dockstore下载工作流 |
| get_docker_image_urlC | 获取 Docker 镜像的完整 URL |
| build_docker_imageD | 构建 Docker 镜像 |
| check_build_statusB | 检查 Docker 镜像构建状态 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 22 tools
Most tools have distinct purposes, but there is some overlap between 'check_workflow_import_status' and 'check_workflow_run_status' which could cause confusion in monitoring workflows. Additionally, 'compose_input_json' and 'generate_inputs_json_template_bioos' both handle input JSON generation, though their descriptions suggest different contexts (user-provided values vs. template generation). Overall, the tools are well-differentiated, but a few pairs require careful reading to avoid misselection.
The naming follows a mostly consistent verb_noun pattern (e.g., 'build_docker_image', 'create_workspace_bioos'), but there are deviations such as 'fetch_wdl_from_dockstore' (verb_noun_preposition) and mixed use of underscores with terms like 'Bio-OS' in names (e.g., 'export_bioos_workspace'). While readable, the lack of a strict convention across all tools reduces predictability.
With 22 tools, the count is on the higher side but reasonable for a comprehensive bioinformatics platform covering Docker builds, workspace management, workflow handling, and IES instances. It feels slightly heavy but not excessive, as each tool appears to serve a specific function in the domain without obvious redundancy.
The tool set provides complete coverage for the bioinformatics domain, including CRUD operations for workspaces and IES instances, workflow lifecycle management (import, validate, submit, monitor, delete), and supporting utilities like Docker image handling and input generation. No significant gaps are apparent; agents can perform end-to-end tasks without dead ends.