Log Analyzer with MCP is a Model Context Protocol server that lets AI assistants access and analyze AWS CloudWatch Logs. It supports browsing log groups, searching with CloudWatch Logs Insights, summarizing logs, finding error patterns, and correlating events across AWS services. The catalogue add-ons provide instructions for using this server with coding agents.
Borrowing it
Nothing to install: this file belongs to awslabs/Log-Analyzer-with-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/awslabs/Log-Analyzer-with-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/awslabs/Log-Analyzer-with-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/awslabs/log-analyzer-with-mcp/claude-md)<a href="https://agentmods.dev/instructions/awslabs/log-analyzer-with-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/awslabs/log-analyzer-with-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/awslabs/log-analyzer-with-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/awslabs/log-analyzer-with-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01332 | $0.01332 |
| Opus 5 | $0.00666 | $0.00666 |
| Sonnet 5 | $0.00266 | $0.00266 |
| Haiku 4.5 | $0.00133 | $0.00133 |
Grade A, and why
Log-Analyzer-with-MCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Log-Analyzer-with-MCP is an MCP (Model Context Protocol) server that provides AI assistants access to AWS CloudWatch Logs for searching, analysis, and cross-service correlation.
Commands
Installation & Setup
uv sync # Install dependencies
source .venv/bin/activate # Activate virtual environment
Running the Server
# Via uvx (recommended for users)
uvx --from git+https://github.com/awslabs/Log-Analyzer-with-MCP cw-mcp-server [--profile PROFILE] [--region REGION] [--stateless]
# Local development
python -m cw_mcp_server.server [--profile PROFILE] [--region REGION] [--stateless]
Linting & Formatting
pre-commit run --all-files # Run ruff linting and formatting
CLI Client (for testing)
python src/client.py list-groups [--prefix PREFIX]
python src/client.py search LOG_GROUP "query" [--hours N]
python src/client.py summarize LOG_GROUP [--hours N]
python src/client.py find-errors LOG_GROUP
python src/client.py correlate LOG_GROUP1 LOG_GROUP2 "search_term"
Architecture
Core Components
src/
├── client.py # Standalone CLI client for testing
└── cw_mcp_server/
├── server.py # Main MCP server entry point
├── resources/
│ └── cloudwatch_logs_resource.py # CloudWatch data as MCP resources
└── tools/
├── __init__.py # @handle_exceptions decorator
├── utils.py # Time range parsing utilities
├── search_tools.py # Log search/query tools
├── analysis_tools.py # Log analysis tools
└── correlation_tools.py # Cross-service correlation
Data Flow
AI Assistant / CLI Client → MCP Server (server.py) → Tool Classes → boto3 CloudWatch Logs Client → AWS
Key Patterns
- AWS Config Decorator:
@with_aws_config()wraps tools to handle AWS profile/region override per-call - Exception Handling:
@handle_exceptionsintools/__init__.pyreturns JSON errors instead of raising exceptions - Async Operations: All tool methods are async for CloudWatch Insights query polling
- Resource URIs: MCP resources exposed via URIs like
logs://groups/{name},logs://groups/{name}/streams - Time Range Flexibility: Tools accept either
hoursoffset orstart_time/end_timeISO8601 timestamps
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 153 lines · 1,332 tokens per session scan A bc27b8b8db2a
Log-Analyzer-with-MCP CLAUDE.md is an instructions file published in the GitHub repository awslabs/Log-Analyzer-with-MCP (167 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,332 tokens to every session, about $0.0067 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.