Atlas / MCP servers / serkanh / CloudWatch Logs

CloudWatch LogsSAFE

mcp/serkanh/cloudwatch-logs
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
2 2r · 0w · 0d
Transport
stdio
License
—
Stars
27
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

An MCP (Model Context Protocol) server that provides tools for accessing AWS CloudWatch logs. This server allows AI assistants to list log groups and read log entries from AWS CloudWatch.

Available Tools

list_groups

Lists available CloudWatch log groups.

Parameters:

  • prefix (optional): Log group name prefix
  • region (optional): AWS region
  • accessKeyId (optional): AWS access key ID
  • secretAccessKey (optional): AWS secret access key
  • sessionToken (optional): AWS session token

Returns: JSON string with the list of log groups, including logGroupName, creationTime, and storedBytes.

get_logs

Gets CloudWatch logs from a specific log group.

Parameters:

  • logGroupName (required): The name of the log group
  • logStreamName (optional): The name of the log stream
  • startTime (optional): Start time in ISO format or relative time (e.g., "5m", "1h", "1d")
  • endTime (optional): End time in ISO format
  • filterPattern (optional): Filter pattern for the logs
  • region (optional): AWS region
  • accessKeyId (optional): AWS access key ID
  • secretAccessKey (optional): AWS secret access key
  • sessionToken (optional): AWS session token

Returns: JSON string with the log events, including timestamp, message, and logStreamName.

Setup

AWS Credentials

Ensure you have AWS credentials configured. You can set them up using the AWS CLI or by setting environment variables:

  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY

Usage with Claude Desktop

Add the following to your claude_desktop_config.json:

{
"mcpServers": {
"cloudwatch-logs": {
"command": "python3",
"args": ["/path/to/cloudwatch-logs-mcp/main.py"],
"env": {
"AWS_ACCESS_KEY_ID": "",
"AWS_SECRET_ACCESS_KEY": "",
},
"disabled": false,
"autoApprove": []
}
}
}

Docker

If you prefer to run the serv

Read from source at commit df8c27fb0609OBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add cloudwatch-logs-mcp -- uvx cloudwatch-logs-mcp
claude-desktop
{
  "mcpServers": {
    "cloudwatch-logs-mcp": {
      "command": "uvx",
      "args": [
        "cloudwatch-logs-mcp"
      ]
    }
  }
}
03

Exposed tools (2)

2 read · 0 write · 0 destructive.

ToolRiskDescription
get_logsreadGet CloudWatch logs from a specific log group and stream.
list_groupsreadList available CloudWatch log groups.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

LOWInventory / provenance · inv.no_license · CWE-1104
Why it matters. no LICENSE file and no repo licence
Fix. add a licence

Gates applied: no_behavioural_pass, no_license.

Audited 2026-10-08 · audit v0.4.1 · source sha df8c27fb0609full audit observations/trust-audit/mcp-server/serkanh__cloudwatch-logs.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-08df8c27fb0609SAFEB89first audit
06

Questions

What tools does CloudWatch Logs expose?

2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is CloudWatch Logs safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does CloudWatch Logs need?

No credential environment variables were found in its source, so it appears to need none.

How does CloudWatch Logs run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as cloudwatch-logs-mcp.

How current is this page?

The grade is for one exact copy of the source (df8c27fb0609), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement