Lint multi-file WDL or CWL workflow bundles and return validation findings. This tool validates multi-file workflow bundles using appropriate linting tools: - WDL workflows: Uses miniwdl package for parsing and validation with import support - CWL workflows: Uses cwltool package for parsing and ...
Bulk/mass operation — affects multiple targets
Part of the AWS HealthOmics MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call LintAHOWorkflowBundle to retrieve information from AWS HealthOmics MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though LintAHOWorkflowBundle only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
LintAHOWorkflowBundle:
rules:
- action: allowSee the full AWS HealthOmics MCP Server policy for all 73 tools.
Agents calling read-class tools like LintAHOWorkflowBundle have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Lint multi-file WDL or CWL workflow bundles and return validation findings. This tool validates multi-file workflow bundles using appropriate linting tools: - WDL workflows: Uses miniwdl package for parsing and validation with import support - CWL workflows: Uses cwltool package for parsing and validation with dependency resolution The tool creates a temporary directory structure that preserves the relative file paths, allowing proper resolution of imports and dependencies between workflow files. The tool checks for: - Syntax errors and parsing issues across all files - Missing required fields (inputs, outputs, steps) - Import/dependency resolution - Runtime requirements for tasks - Common workflow structure issues Args: ctx: MCP context for error reporting workflow_files: Dictionary mapping relative file paths to their content, a local directory path, a ZIP file path, or an S3 URI (s3://bucket/prefix/ or s3://bucket/file.zip). workflow_format: The workflow format ('wdl' or 'cwl') main_workflow_file: Path to the main workflow file within the bundle Returns: Dictionary containing: - status: 'success' or 'error' - format: The workflow format that was linted - main_file: The main workflow file that was processed - files_processed: List of all files that were processed - linter: Name of the linting tool used - raw_output: Raw output from the linter command execution. It is categorised as a Read tool in the AWS HealthOmics MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for LintAHOWorkflowBundle. 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.
LintAHOWorkflowBundle is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the LintAHOWorkflowBundle 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.
Set action: deny in the Intercept policy for LintAHOWorkflowBundle. 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.
LintAHOWorkflowBundle 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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.