mcpSource-backedReview first Safety ✓ Privacy ✓

AWS CloudTrail MCP Server

Official AWS Labs MCP server for AWS CloudTrail that lets AI assistants query account activity for security investigations, compliance auditing, and operational troubleshooting via Event History and CloudTrail Lake SQL.

by AWS Labs·added 2026-06-21·

Claude Code Codex Cursor Claude Desktop

HarnessClaude CodeCodexCursorClaude Desktop

Install

Source

uvx awslabs.cloudtrail-mcp-server@latest

Readiness

TrustReview first
Sourcesource-backed
Safety notesPresent
ReviewedYes

Documentation Source repository Registry JSON · LLM text

Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL: https://heyclau.de/entry/mcp/aws-cloudtrail-mcp-server
Source URLs: https://github.com/awslabs/mcp/blob/main/src/cloudtrail-mcp-server/README.md, https://github.com/awslabs/mcp, https://awslabs.github.io/mcp/
Brand: AWS Labs
Brand domain: aws.amazon.com
Brand asset source: brandfetch
Safety notes: The provided tools are read-only — they look up CloudTrail events and run Lake queries, and do not modify infrastructure. Grant only the CloudTrail read permissions listed in the documentation (least privilege)., This server reads audit data with your AWS credentials; scope the profile to the intended account and run it only on a trusted host., CloudTrail Lake SQL queries against large event data stores can incur AWS query/scan costs; review query scope before running broad analyses.
Privacy notes: CloudTrail events expose account activity: usernames, access key IDs, source IPs, ARNs, and API call details can be returned to the model., Keep account identifiers, credentials, and returned event contents out of public prompts, issues, and screenshots, since audit data is sensitive.
Author: AWS Labs
Submitted by: jaso0n0818
Claim status: unclaimed
Last verified: 2026-06-21

Safety notes

The provided tools are read-only — they look up CloudTrail events and run Lake queries, and do not modify infrastructure. Grant only the CloudTrail read permissions listed in the documentation (least privilege).
This server reads audit data with your AWS credentials; scope the profile to the intended account and run it only on a trusted host.
CloudTrail Lake SQL queries against large event data stores can incur AWS query/scan costs; review query scope before running broad analyses.

Privacy notes

CloudTrail events expose account activity: usernames, access key IDs, source IPs, ARNs, and API call details can be returned to the model.
Keep account identifiers, credentials, and returned event contents out of public prompts, issues, and screenshots, since audit data is sensitive.

Prerequisites

An AWS account with CloudTrail enabled (Event History is on by default; CloudTrail Lake is needed for SQL queries).
Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package.
AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) with CloudTrail read permissions (`cloudtrail:LookupEvents`, `cloudtrail:StartQuery`, `cloudtrail:GetQueryResults`, and related).
An MCP client that supports stdio servers; the server runs locally on the same host as the client.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 10 minutes
Difficulty: intermediate

Tool listing metadata

Website: https://awslabs.github.io/mcp/
Pricing: open-source
Disclosure: editorial
Application category: DeveloperApplication
Operating system: Cross-platform

Full copyable content

{
  "awslabs.cloudtrail-mcp-server": {
    "command": "uvx",
    "args": ["awslabs.cloudtrail-mcp-server@latest"],
    "env": {
      "AWS_PROFILE": "${AWS_PROFILE}",
      "FASTMCP_LOG_LEVEL": "ERROR"
    }
  }
}

About this resource

Overview

AWS CloudTrail MCP Server is an official AWS Labs Model Context Protocol server that lets AI assistants query AWS account activity for security investigations, compliance auditing, and operational troubleshooting. It provides access to CloudTrail Event History and CloudTrail Lake analytics so agents can track API calls and analyze user activity through standardized MCP tools.

It runs locally over stdio via uvx from the published awslabs.cloudtrail-mcp-server Python package and uses your local AWS credentials. The provided tools are read-only.

Features

Event lookup — search CloudTrail events by username, event name, resource name, and more, across the last 90 days of management events.
CloudTrail Lake analytics — run Trino-compatible SQL queries against CloudTrail Lake for complex filtering and aggregation.
User activity analysis — track activity by username, access key, or other user attributes.
API call tracking — monitor specific API calls and their patterns for security and compliance.
Event data store management — list and explore CloudTrail Lake event data stores and their capabilities.

Use Cases

Investigate a security incident by tracing who called which API and when.
Audit user activity across AWS services for compliance.
Run an ad hoc CloudTrail Lake SQL query for deeper analysis.
Troubleshoot an operational change by finding the API calls that caused it.

Installation

Claude Code

Install Python 3.10+ and uv.
Configure an AWS profile with CloudTrail read permissions.
Add the server with the stdio configuration above (command uvx, package awslabs.cloudtrail-mcp-server@latest, env AWS_PROFILE).
Verify it is connected with claude mcp list.

Claude Desktop / Cursor / Kiro / VS Code

Add the configSnippet above to your client's MCP configuration and set AWS_PROFILE. The first run downloads the package via uvx.

Source And Trust

This entry is based on the official AWS Labs awslabs/mcp repository and the published PyPI package (Apache-2.0). The server is read-only over CloudTrail, but it uses your AWS credentials and returns sensitive audit data, so scope permissions to CloudTrail reads, keep results private, and verify the configuration against the linked source before using it in automated workflows.

#aws #cloudtrail #security #audit #aws-labs

Source citations

Source methodology →

Add this badge to your README

Show that AWS CloudTrail MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/aws-cloudtrail-mcp-server.svg)](https://heyclau.de/entry/mcp/aws-cloudtrail-mcp-server)

How it compares

AWS CloudTrail MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	AWS CloudTrail MCP Server Official AWS Labs MCP server for AWS CloudTrail that lets AI assistants query account activity for security investigations, compliance auditing, and operational troubleshooting via Event History and CloudTrail Lake SQL. Open dossier	AWS IAM MCP Server Official AWS Labs MCP server for AWS Identity and Access Management that lets AI assistants inspect and manage IAM users, roles, groups, policies, and access keys, with policy simulation and an opt-in read-only mode. Open dossier	AWS S3 Tables MCP Server Official AWS Labs MCP server for AWS S3 Tables that lets AI assistants create and query S3-based tables, run read-only SQL for analysis, generate tables from CSV files in S3, and explore table metadata — read-only by default. Open dossier	Amazon ECS MCP Server Official AWS Labs MCP server for Amazon ECS that helps AI assistants containerize applications, deploy them to ECS, troubleshoot deployments, and explore ECS and ECR resources across the container application lifecycle. Open dossier
Trust
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	AWS Labs	AWS Labs	AWS Labs	AWS Labs
Category	mcp	mcp	mcp	mcp
Source	source-backed	source-backed	source-backed	source-backed
Author	AWS Labs	AWS Labs	AWS Labs	AWS Labs
Added	2026-06-21	2026-06-21	2026-06-21	2026-06-21
Platforms	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Source repo	—	—	—	—
Safety notes	✓The provided tools are read-only — they look up CloudTrail events and run Lake queries, and do not modify infrastructure. Grant only the CloudTrail read permissions listed in the documentation (least privilege). This server reads audit data with your AWS credentials; scope the profile to the intended account and run it only on a trusted host. CloudTrail Lake SQL queries against large event data stores can incur AWS query/scan costs; review query scope before running broad analyses.	✓Run with the `--readonly` flag (shown above) to block all mutating operations. Without it the server can create and delete IAM users, roles, groups, policies, and access keys — high-impact identity changes — so enable write access only deliberately and with scoped permissions. IAM controls account-wide access; a misused write operation can grant or revoke permissions broadly. Prefer non-production accounts while evaluating, and use policy simulation to test changes before applying them. This server acts on real IAM with your AWS credentials; scope the profile tightly and run it only on a trusted host.	✓The server is read-only by default. Adding the `--allow-write` flag (with the matching IAM permissions) enables create and append operations on S3 Tables; there is no delete or general update. Enable write only deliberately. AWS advises that you are responsible for your agents: if you enable write, back up your data first and validate LLM-generated instructions before execution, since misconfigured permissions can cause data loss. This server acts on real S3 Tables data with your AWS credentials; scope the profile least-privilege and run it only on a trusted host.	✓The configuration above is read-only. Setting `ALLOW_WRITE=true` lets the server create and modify infrastructure (ECR repos, CloudFormation stacks, ECS services) and `ALLOW_SENSITIVE_DATA=true` exposes logs; enable these only deliberately. AWS documents this server as primarily for development, testing, and non-critical environments; keep write/sensitive-data disabled for production accounts and prefer non-production targets while evaluating it. This server acts on real infrastructure with your AWS credentials; scope the profile to the intended account, region, and resources, and run it only on a trusted host.
Privacy notes	✓CloudTrail events expose account activity: usernames, access key IDs, source IPs, ARNs, and API call details can be returned to the model. Keep account identifiers, credentials, and returned event contents out of public prompts, issues, and screenshots, since audit data is sensitive.	✓IAM user/role/group names, ARNs, policy documents, and account metadata can be returned through tool calls and exposed to the model. Access key IDs and other identity material may appear in responses; never expose secret access keys, and keep account identifiers and policy contents out of public prompts, issues, and screenshots.	✓Table schemas, metadata, query results, and bucket/namespace identifiers can be returned through tool calls and exposed to the model. Keep account identifiers, credentials, and any sensitive table data out of public prompts, issues, and screenshots.	✓Cluster, service, task, task-definition, and ECR metadata plus account/region identifiers can be returned through tool calls and exposed to the model. With sensitive-data access enabled, logs and deployment details may be returned; keep account identifiers, credentials, and log contents out of public prompts, issues, and screenshots.
Prerequisites	An AWS account with CloudTrail enabled (Event History is on by default; CloudTrail Lake is needed for SQL queries). Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package. AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) with CloudTrail read permissions (`cloudtrail:LookupEvents`, `cloudtrail:StartQuery`, `cloudtrail:GetQueryResults`, and related). An MCP client that supports stdio servers; the server runs locally on the same host as the client.	An AWS account with IAM access and permissions for the IAM read (and, if write is enabled, manage) operations you intend to use. Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package. AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) scoped least-privilege; read-only IAM permissions are enough for the recommended `--readonly` mode. An MCP client that supports stdio servers; the server runs locally on the same host as the client.	An AWS account with S3 Tables and permissions for the table buckets you intend to read (and, if enabled, write). Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package. AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) scoped least-privilege to the intended S3 Tables resources. An MCP client that supports stdio servers; the server runs locally on the same host as the client.	An AWS account with Amazon ECS/ECR and permissions to view (and, if enabled, deploy) the target resources. Docker or Finch for containerization and local image builds. Python 3.10 or newer and `uv` / `uvx` installed (Astral) to run the package. AWS credentials configured locally (for example via `aws configure` or `AWS_PROFILE`) scoped to the intended account, region, and resources.
Install	`uvx awslabs.cloudtrail-mcp-server@latest`	`uvx awslabs.iam-mcp-server@latest --readonly`	`uvx awslabs.s3-tables-mcp-server@latest`	`uvx --from awslabs-ecs-mcp-server ecs-mcp-server`
Config	`{ "mcpServers": { "awslabs.cloudtrail-mcp-server": { "command": "uvx", "args": ["awslabs.cloudtrail-mcp-server@latest"], "env": { "AWS_PROFILE": "${AWS_PROFILE}", "FASTMCP_LOG_LEVEL": "ERROR" }, "type": "stdio" } } }`	`{ "mcpServers": { "awslabs.iam-mcp-server": { "command": "uvx", "args": ["awslabs.iam-mcp-server@latest", "--readonly"], "env": { "AWS_PROFILE": "${AWS_PROFILE}", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR" }, "type": "stdio" } } }`	`{ "mcpServers": { "awslabs.s3-tables-mcp-server": { "command": "uvx", "args": ["awslabs.s3-tables-mcp-server@latest"], "env": { "AWS_PROFILE": "${AWS_PROFILE}", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR" }, "type": "stdio" } } }`	`{ "mcpServers": { "awslabs.ecs-mcp-server": { "command": "uvx", "args": ["--from", "awslabs-ecs-mcp-server", "ecs-mcp-server"], "env": { "AWS_PROFILE": "${AWS_PROFILE}", "AWS_REGION": "us-east-1", "FASTMCP_LOG_LEVEL": "ERROR", "ALLOW_WRITE": "false", "ALLOW_SENSITIVE_DATA": "false" }, "type": "stdio" } } }`
Citations	Source repositorygithub.com 2026-06-22T23:55:05-07:00 Documentationgithub.com Websiteawslabs.github.io Submitted by jaso0n08182026-06-21 Source methodology →	Source repositorygithub.com 2026-06-22T23:55:05-07:00 Documentationgithub.com Submitted by jaso0n08182026-06-21 Source methodology →	Source repositorygithub.com 2026-06-22T23:55:05-07:00 Documentationgithub.com Submitted by jaso0n08182026-06-21 Source methodology →	Source repositorygithub.com 2026-06-22T23:55:05-07:00 Documentationgithub.com Submitted by jaso0n08182026-06-21 Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed