Medium Risk

add_inline_policy

Add a new inline policy to an IAM role. This tool creates a new inline policy with the specified permissions and adds it to an IAM role. Inline policies are embedded within the role and cannot be attached to multiple roles. Commonly used for granting EKS clusters access to AWS services, enabling...

Single-target operation

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

AI agents use add_inline_policy to create or modify resources in Amazon EKS 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 add_inline_policy 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 EKS MCP Server.

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

amazon-eks-mcp-server.yaml
tools:
  add_inline_policy:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Amazon EKS MCP Server policy for all 16 tools.

Tool Name add_inline_policy
Category Write
Risk Level Medium

View all 16 tools →

Agents calling write-class tools like add_inline_policy 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 add_inline_policy tool do? +

Add a new inline policy to an IAM role. This tool creates a new inline policy with the specified permissions and adds it to an IAM role. Inline policies are embedded within the role and cannot be attached to multiple roles. Commonly used for granting EKS clusters access to AWS services, enabling worker nodes to access resources, and configuring permissions for CloudWatch logging and ECR access. IMPORTANT: Use this tool instead of 'aws iam put-role-policy' commands. ## Requirements - The server must be run with the `--allow-write` flag - The role must exist in your AWS account - The policy name must be unique within the role - You cannot modify existing policies with this tool ## Permission Format The permissions parameter can be either a single policy statement or a list of statements. ### Single Statement Example ```json { "Effect": "Allow", "Action": ["s3:GetObject", "s3:PutObject"], "Resource": "arn:aws:s3:::example-bucket/*" } ``` ## Usage Tips - Follow the principle of least privilege by granting only necessary permissions - Use specific resources rather than "*" whenever possible - Consider using conditions to further restrict permissions - Group related permissions into logical policies with descriptive names Args: ctx: The MCP context policy_name: Name of the new inline policy to create role_name: Name of the role to add the policy to permissions: Permissions to include in the policy (in JSON format) Returns: AddInlinePolicyResponse: Information about the created policy. It is categorised as a Write tool in the Amazon EKS 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 add_inline_policy? +

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

What risk level is add_inline_policy? +

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

Can I rate-limit add_inline_policy? +

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

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

add_inline_policy is provided by the Amazon EKS MCP Server MCP server (awslabs.eks-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.