// SCAN REPORT

AWS HealthOmics MCP Server

73 tools. 26 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 28 May 2026

26 can modify or destroy data

47 read-only

73 tools total

// TOOL MAP

Read (47) Write / Execute (22) Destructive / Financial (4)

// WHAT CAN GO WRONG

Destructive tools (CancelAHORunBatch, DeleteAHOBatch, DeleteAHOConfiguration) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (ActivateAHOReadSets, CreateAHOConfiguration, CreateAHORunCache) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (DiagnoseAHORunFailure, StartAHOReadSetExportJob, StartAHOReadSetImportJob) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

// RECOMMENDED RULES

Deny destructive operations

CancelAHORunBatch:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

ActivateAHOReadSets:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

AnalyzeAHORunPerformance:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

// ALL 73 AWS HEALTHOMICS MCP SERVER TOOLS

DESTRUCTIVE 4 tools

Destructive CancelAHORunBatch Destructive DeleteAHOBatch Destructive DeleteAHOConfiguration Destructive DeleteAHORunBatch

EXECUTE 6 tools

Execute DiagnoseAHORunFailure Execute StartAHOReadSetExportJob Execute StartAHOReadSetImportJob Execute StartAHOReferenceImportJob Execute StartAHORun Execute StartAHORunBatch

WRITE 16 tools

Write ActivateAHOReadSets Write CreateAHOConfiguration Write CreateAHORunCache Write CreateAHORunGroup Write CreateAHOSequenceStore Write CreateAHOWorkflow Write CreateAHOWorkflowVersion Write CreateCodeConnection Write CreateContainerRegistryMap Write CreatePullThroughCacheForHealthOmics Write GenerateAHORunTimeline Write GrantHealthOmicsRepositoryAccess Write PackageAHOWorkflow Write UpdateAHORunCache Write UpdateAHORunGroup Write UpdateAHOSequenceStore

READ 47 tools

Read AnalyzeAHORunPerformance Read CheckContainerAvailability Read CloneContainerToECR Read GetAHOBatch Read GetAHOConfiguration Read GetAHOReadSetExportJob Read GetAHOReadSetImportJob Read GetAHOReadSetMetadata Read GetAHOReferenceImportJob Read GetAHOReferenceMetadata Read GetAHOReferenceStore Read GetAHORun Read GetAHORunCache Read GetAHORunEngineLogs Read GetAHORunGroup Read GetAHORunLogs Read GetAHORunManifestLogs Read GetAHORunTask Read GetAHOSequenceStore Read GetAHOSupportedRegions Read GetAHOTaskLogs Read GetAHOWorkflow Read GetCodeConnection Read GetSupportedFileTypes Read LintAHOWorkflowBundle Read LintAHOWorkflowDefinition Read ListAHOBatches Read ListAHOConfigurations Read ListAHOReadSetExportJobs Read ListAHOReadSetImportJobs Read ListAHOReadSets Read ListAHOReferenceImportJobs Read ListAHOReferences Read ListAHOReferenceStores Read ListAHORunCaches Read ListAHORunGroups Read ListAHORuns Read ListAHORunsInBatch Read ListAHORunTasks Read ListAHOSequenceStores Read ListAHOWorkflows Read ListAHOWorkflowVersions Read ListCodeConnections Read ListECRRepositories Read ListPullThroughCacheRules Read SearchGenomicsFiles Read ValidateHealthOmicsECRConfig

// FAQ

Can an AI agent delete data through the AWS HealthOmics MCP Server MCP server? +

Yes. The AWS HealthOmics MCP Server server exposes 4 destructive tools including CancelAHORunBatch, DeleteAHOBatch, DeleteAHOConfiguration. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through AWS HealthOmics MCP Server? +

The AWS HealthOmics MCP Server server has 16 write tools including ActivateAHOReadSets, CreateAHOConfiguration, CreateAHORunCache. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the AWS HealthOmics MCP Server MCP server expose? +

73 tools across 4 categories: Destructive, Execute, Read, Write. 47 are read-only. 26 can modify, create, or delete data.

How do I add Intercept to my AWS HealthOmics MCP Server setup? +

One line change. Instead of running the AWS HealthOmics MCP Server server directly, prefix it with Intercept: intercept -c aws-healthomics-mcp-server.yaml -- npx -y @awslabs.aws-healthomics-mcp-server. Download a pre-built policy from policylayer.com/policies/aws-healthomics-mcp-server and adjust the limits to match your use case.

AWS HealthOmics MCP Server

Other MCP servers with similar tools.

Let agents act without letting them run wild.