Medium Risk

connect-jump-host-cache-cluster

Configures an existing EC2 instance as a jump host to access an ElastiCache cluster. Args: cache_cluster_id (str): ID of the ElastiCache cluster to connect to instance_id (str): ID of the EC2 instance to use as jump host Returns: Dict[str, Any]: Dictionary containing connection deta...

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

AI agents use connect-jump-host-cache-cluster to create or modify resources in AWS ElastiCache 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 connect-jump-host-cache-cluster 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 ElastiCache MCP Server.

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

aws-elasticache-mcp-server.yaml
tools:
  connect-jump-host-cache-cluster:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full AWS ElastiCache MCP Server policy for all 39 tools.

Tool Name connect-jump-host-cache-cluster
Category Write
Risk Level Medium

View all 39 tools →

Agents calling write-class tools like connect-jump-host-cache-cluster 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 connect-jump-host-cache-cluster tool do? +

Configures an existing EC2 instance as a jump host to access an ElastiCache cluster. Args: cache_cluster_id (str): ID of the ElastiCache cluster to connect to instance_id (str): ID of the EC2 instance to use as jump host Returns: Dict[str, Any]: Dictionary containing connection details and configuration status Raises: ValueError: If VPC compatibility check fails or required resources not found. It is categorised as a Write tool in the AWS ElastiCache 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 connect-jump-host-cache-cluster? +

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

What risk level is connect-jump-host-cache-cluster? +

connect-jump-host-cache-cluster is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit connect-jump-host-cache-cluster? +

Yes. Add a rate_limit block to the connect-jump-host-cache-cluster 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 connect-jump-host-cache-cluster completely? +

Set action: deny in the Intercept policy for connect-jump-host-cache-cluster. 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 connect-jump-host-cache-cluster? +

connect-jump-host-cache-cluster is provided by the AWS ElastiCache MCP Server MCP server (awslabs.elasticache-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.