Bio MCP Server

The MCP Servers for Bio-OS instance platforms.

Local serverstdioPython

What is the Bio MCP server?

If you already use Bio, the bio mcp server is the piece that lets your assistant work with it directly. The MCP Servers for Bio-OS instance platforms.

What the server does

A Model Context Protocol (MCP) based tool and prompt server for Bio-OS that provides workflow management and Docker image building capabilities.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Function — Submit Bio-OS workflow
  • Parameters — - ak: Access Key
  • workspace_name — Workspace name
  • workflow_name — Workflow name
  • input_json — Input JSON file path
  • workflow_source — WDL file path
  • workflow_desc — Workflow description
  • namespace_name — Namespace
  • repo_name — Repository name
  • tag — Version tag
  • source_path — Dockerfile or archive path
  • Prerequisites — 1. Install uv (Python package manager): bash pip install uv

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Credentials and setup notes

Configuration is passed through the environment: PYTHONPATH, MIRACLE_ACCESS_KEY, MIRACLE_SECRET_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Bio-OS MCP Server requires the following dependencies: 1. Install uv (Python package manager): 2. Install Cromwell (Workflow execution engine):

Where it fits

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Bio's toolset — Function, Parameters, workspace_name and 11 more — is a fair guide to whether it matches your workflow. It is maintained by GBA-BI; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Bio.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
FunctionSubmit Bio-OS workflow
Parameters- ak: Access Key
workspace_nameWorkspace name
workflow_nameWorkflow name
input_jsonInput JSON file path
workflow_sourceWDL file path
workflow_descWorkflow description
namespace_nameNamespace
repo_nameRepository name
tagVersion tag
source_pathDockerfile or archive path
Prerequisites1. Install uv (Python package manager): bash pip install uv
InstallationClone the Bio-OS MCP Server repository: bash git clone https://github.com/GBA-BI/bioos-mcp-server.git
ConfigurationConfigure the Bio-OS MCP Server script path in CLINE's MCP settings. Replace the placeholders with absolute paths to your installation: json { "mcpServers": { "bioos": { "command": "path/to/uv", "args": [ "--directory",

Configuration

Bio-OS MCP Server requires the following dependencies: 1. Install uv (Python package manager): 2. Install Cromwell (Workflow execution engine):

VariableDescriptionRequired
PYTHONPATHFilesystem location the server is allowed to use.Optional
MIRACLE_ACCESS_KEYCredential the server authenticates with.Yes
MIRACLE_SECRET_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Bio to Function.
  • Use Bio to Parameters.
  • Use Bio to workspace name.

Frequently asked questions

It requires uv (Python package manager) and Cromwell (workflow execution engine).