manage_aws_glue_connection_metadata

// WHEN AI AGENTS USE THIS TOOL

AI agents use manage_aws_glue_connection_metadata to create or modify resources in Amazon Data Processing 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.

// WHY ENFORCE A POLICY ON MANAGE_AWS_GLUE_CONNECTION_METADATA

Without a policy, an AI agent could call manage_aws_glue_connection_metadata 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 Amazon Data Processing MCP Server.

// RECOMMENDED POLICY

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

amazon-data-processing-mcp-server.yaml

tools:
  manage_aws_glue_connection_metadata:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Amazon Data Processing MCP Server policy for all 36 tools.

// DETAILS

Tool Name manage_aws_glue_connection_metadata

Category Write

MCP Server Amazon Data Processing MCP Server MCP Server

Risk Level Medium

// MORE AMAZON DATA PROCESSING MCP SERVER TOOLS

Write add_inline_policy Write create_data_processing_role Write manage_aws_athena_data_catalogs Write manage_aws_athena_databases_and_tables Write manage_aws_athena_named_queries Write manage_aws_athena_query_executions Write manage_aws_athena_workgroups Write manage_aws_emr_clusters

View all 36 tools →

// WHAT CAN GO WRONG

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

Browse the full MCP Attack Database →

// OTHER WRITE TOOLS ACROSS MCP SERVERS

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

Firecrawl Web Scraping Server firecrawl_generate_llmstxt AbraFlexi contact_create AbraFlexi contact_update AbraFlexi evidence_create AbraFlexi evidence_update AbraFlexi invoice_issued_update

// RELATED READING

// FAQ

What does the manage_aws_glue_connection_metadata tool do? +

Access connection metadata and preview entity data from AWS Glue connections. This tool provides operations for discovering entities available through a connection, describing entity schemas, and previewing entity data. Useful for exploring data sources connected via AWS Glue connections such as SaaS applications, databases, and other data stores. ## Requirements - The server must be run with the `--allow-sensitive-data-access` flag for get-entity-records operation - Appropriate AWS permissions for Glue connection metadata operations - A valid connection with credentials must exist ## Operations - **list-entities**: List available entities (e.g., tables, SObjects) for a connection - **describe-entity**: Get the schema/field details for a specific entity - **get-entity-records**: Preview data records from an entity (requires sensitive data access) ## Example ```python # List entities for a Salesforce connection manage_aws_glue_connection_metadata( operation='list-entities', connection_name='my-salesforce-connection', ) # Describe the Account entity manage_aws_glue_connection_metadata( operation='describe-entity', connection_name='my-salesforce-connection', entity_name='Account', ) # Preview records from the Account entity manage_aws_glue_connection_metadata( operation='get-entity-records', connection_name='my-salesforce-connection', entity_name='Account', limit=10, ) ``` Args: ctx: MCP context operation: Operation to perform connection_name: Name of the connection entity_name: Name of the entity catalog_id: Catalog ID parent_entity_name: Parent entity name for listing children next_token: Pagination token data_store_api_version: API version of the SaaS connector limit: Maximum number of records to fetch connection_options: Connector options for querying data filter_predicate: Filter predicate for the query selected_fields: List of fields to fetch Returns: Union of response types specific to the operation performed. It is categorised as a Write tool in the Amazon Data Processing 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 manage_aws_glue_connection_metadata? +

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

What risk level is manage_aws_glue_connection_metadata? +

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

Can I rate-limit manage_aws_glue_connection_metadata? +

Yes. Add a rate_limit block to the manage_aws_glue_connection_metadata 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 manage_aws_glue_connection_metadata completely? +

Set action: deny in the Intercept policy for manage_aws_glue_connection_metadata. 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 manage_aws_glue_connection_metadata? +

manage_aws_glue_connection_metadata is provided by the Amazon Data Processing MCP Server MCP server (awslabs.aws-dataprocessing-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

manage_aws_glue_connection_metadata

Let agents act without letting them run wild.