Medium Risk

CreateAHOWorkflowVersion

Create a new version of an existing workflow. Args: ctx: MCP context for error reporting workflow_id: ID of the workflow version_name: Name for the new version definition_source: Workflow definition content — a local ZIP file path, S3 URI (s3://bucket/key.zip), or base64-...

High parameter count (22 properties); Single-target operation

Part of the AWS HealthOmics MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents use CreateAHOWorkflowVersion to create or modify resources in AWS HealthOmics MCP Server. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call CreateAHOWorkflowVersion repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach AWS HealthOmics MCP Server.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

aws-healthomics-mcp-server.yaml
tools:
  CreateAHOWorkflowVersion:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full AWS HealthOmics MCP Server policy for all 73 tools.

Tool Name CreateAHOWorkflowVersion
Category Write
Risk Level Medium

View all 73 tools →

Agents calling write-class tools like CreateAHOWorkflowVersion have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the CreateAHOWorkflowVersion tool do? +

Create a new version of an existing workflow. Args: ctx: MCP context for error reporting workflow_id: ID of the workflow version_name: Name for the new version definition_source: Workflow definition content — a local ZIP file path, S3 URI (s3://bucket/key.zip), or base64-encoded ZIP content. Cannot be used together with definition_uri or definition_repository description: Optional description of the workflow version parameter_template: Optional parameter template for the workflow storage_type: Storage type (STATIC or DYNAMIC) storage_capacity: Storage capacity in GB (required for STATIC) container_registry_map: Optional container registry map with registryMappings (upstreamRegistryUrl, ecrRepositoryPrefix, upstreamRepositoryPrefix, ecrAccountId) and imageMappings (sourceImage, destinationImage) arrays container_registry_map_uri: Optional S3 URI pointing to a JSON file containing container registry mappings. Cannot be used together with container_registry_map definition_uri: S3 URI of the workflow definition ZIP file. Cannot be used together with definition_source or definition_repository path_to_main: Path to the main file in the workflow definition ZIP file. Not required if there is a top level main.wdl, main.cwl or main.nf files in the workflow package. Not required if there is only a single top level workflow file. readme: README documentation - can be markdown content, local .md file path, or S3 URI (s3://bucket/key) definition_repository: Git repository configuration with connection_arn, full_repository_id, source_reference, and optional exclude_file_patterns parameter_template_path: Path to parameter template JSON file within the repository (only valid with definition_repository) readme_path: Path to README markdown file within the repository (only valid with definition_repository) engine: Workflow engine type. WDL_LENIENT allows for some WDL directives that don't strictly meet the WDL spec and can be useful when migrating legacy workflows designed to run on Cromwell. tags: Tags to apply to the workflow version as a dict or JSON string accelerators: Computational accelerator type. Currently unused by the HealthOmics service. Reserved for future support. workflow_bucket_owner_id: Expected AWS account ID of the S3 bucket owner definition_zip_base64: **Deprecated** — use definition_source instead. Base64-encoded workflow definition ZIP file. aws_profile: Optional AWS profile name override aws_region: Optional AWS region override Returns: Dictionary containing the created workflow version information. It is categorised as a Write tool in the AWS HealthOmics MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on CreateAHOWorkflowVersion? +

Add a rule in your Intercept YAML policy under the tools section for CreateAHOWorkflowVersion. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS HealthOmics MCP Server MCP server.

What risk level is CreateAHOWorkflowVersion? +

CreateAHOWorkflowVersion is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit CreateAHOWorkflowVersion? +

Yes. Add a rate_limit block to the CreateAHOWorkflowVersion rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block CreateAHOWorkflowVersion completely? +

Set action: deny in the Intercept policy for CreateAHOWorkflowVersion. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides CreateAHOWorkflowVersion? +

CreateAHOWorkflowVersion is provided by the AWS HealthOmics MCP Server MCP server (awslabs.aws-healthomics-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.