AWS CloudWatch
The CloudWatch MCP server provides AI assistants with direct access to AWS CloudWatch resources for monitoring and log analysis. Built with Python using FastMCP, it exposes tools for listing log groups, retrieving alarms (with filtering by state), executing CloudWatch Insights queries across multiple log groups, discovering log fields, and accessing saved queries. The implementation handles authentication through AWS profiles, automatically parses JSON in log messages, and supports both static and dynamic time ranges for queries. This server is particularly valuable for DevOps engineers and system administrators who need to monitor application health, investigate issues through logs, or analyze CloudWatch metrics without switching context from their AI assistant.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/charliefng/cloudwatch-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve AWS CloudWatch from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.