What platforms does Cloudpulse Mcp Server support?
It supports AWS (Lambda, RDS, S3, CloudWatch), GCP (Cloud Run, Cloud SQL, Cloud Logging), Vercel, and Cloudflare (Pages, Workers).
@Galadriel-Tech-Solutions
Basic information
Cross-cloud observability for AI agents. Discover resources, correlate logs, and diagnose infrastructure issues across AWS, GCP, Vercel, and Cloudflare — without leaving your editor.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cloudpulse": {
"command": "npx",
"args": [
"-y",
"cloudpulse-mcp"
],
"env": {
"AWS_ACCESS_KEY_ID": "<your-aws-key>",
"AWS_SECRET_ACCESS_KEY": "<your-aws-secret>",
"AWS_REGION": "us-east-1",
"VERCEL_TOKEN": "<your-vercel-token>",
"GOOGLE_APPLICATION_CREDENTIALS": "<path-to-gcp-json>",
"CLOUDFLARE_API_TOKEN": "<your-cf-token>",
"CLOUDFLARE_ACCOUNT_ID": "<your-cf-account-id>"
}
}
}
}Scan all configured cloud platforms (AWS, Vercel, GCP, Cloudflare) and return a unified topology of active services including their endpoints and regions. Run this first to understand the infrastructure landscape.
Fetch logs from multiple cloud platforms (AWS CloudWatch + Vercel) for a given time window and optional trace ID, then merge them into a single chronological timeline. Use this to correlate errors across frontend and backend services.
Diagnose connectivity issues between a source service and a target resource. Checks Vercel environment variables, AWS Security Group inbound rules on the required port, and external API reachability. Returns a list of diagnostic results with actionable messages.
Query quota limits and current usage across configured cloud platforms. Highlights resources approaching or exceeding their limits (default warning threshold: 80%). Use this to proactively catch Lambda concurrency limits, Vercel plan caps, and similar issues before they cause outages.
CloudPulse is an open-source MCP Server that gives AI agents cross-cloud visibility through a single tool. It integrates with AWS, GCP, Vercel, and Cloudflare to provide a unified view of cloud resources, logs, and connectivity.
The server exposes four built-in tools: list_cloud_topology (scan all configured platforms and return a unified service map), get_correlated_logs (fetch and merge logs from multiple providers into one timeline), diagnose_service_link (check why service A can't reach resource B with security groups, CORS, env vars, authorized networks), and check_resource_limits (query quotas across all platforms and flag resources nearing limits). Configuration details for authentication and platform setup are not included in the README.
It supports AWS (Lambda, RDS, S3, CloudWatch), GCP (Cloud Run, Cloud SQL, Cloud Logging), Vercel, and Cloudflare (Pages, Workers).
Yes, by default the server operates in read-only mode. No destructive operations are exposed in the provided tools.
No, according to the README, no credentials are stored or logged by the server.
Four built-in tools: `list_cloud_topology`, `get_correlated_logs`, `diagnose_service_link`, and `check_resource_limits`.
Yes, the `diagnose_service_link` tool checks why a service cannot reach a resource, examining security groups, CORS, environment variables, and authorized networks.
MCP server connecting to Kubernetes
A docker MCP Server (modelcontextprotocol)
Official OutageDeck MCP server for vendor-published cloud and SaaS status, incident timelines, and observed uptime history.

InfraNest watches your websites, servers, domains and SSL certificates. Connect it to Claude, ChatGPT or Cursor and ask what is down or about to expire.
Comments