Which integrations are available for this server?

Provides cross-cloud infrastructure visibility for Cloudflare services including Workers and Pages, enabling AI agents to diagnose issues and inspect configurations without leaving the editor. Enables inspection and monitoring of Cloudflare Workers, including tail logs via WebSocket, as part of cross-cloud infrastructure diagnostics. Supports integration with GitHub Copilot in Agent Mode, allowing users to access CloudPulse tools directly through Copilot Chat for natural language infrastructure diagnostics. Provides comprehensive Vercel integration including project inspection, environment variable checking, log correlation with AWS, and service link diagnostics for Vercel deployments.

CloudPulse MCP Server

Cross-cloud infrastructure visibility for AI agents. Diagnose issues across AWS, Vercel, GCP, and Cloudflare without ever leaving your editor.

License: MIT Node.js ≥18

Why CloudPulse?

Pain point	CloudPulse fix
Frontend error on Vercel → must open AWS console	`get_correlated_logs` merges both timelines automatically
AI can't see if an SG blocks port 5432	`diagnose_service_link` inspects the security group rules live
Hitting Lambda concurrency limits silently	`check_resource_limits` warns at 80% usage
Topology unknown before debugging	`list_cloud_topology` maps every active service in seconds

Quick Start

1. Install / run with npx

npx cloudpulse-mcp

The server auto-detects credentials already present on your machine (AWS CLI, environment variables, etc.).

2. Configure your AI client

Claude Desktop – add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "cloudpulse": {
      "command": "npx",
      "args": ["-y", "cloudpulse-mcp"],
      "env": {
        "VERCEL_TOKEN": "<your-vercel-token>",
        "AWS_PROFILE": "default",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Cursor – add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "cloudpulse": {
      "command": "npx",
      "args": ["-y", "cloudpulse-mcp"],
      "env": {
        "VERCEL_TOKEN": "<your-vercel-token>",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

VS Code + GitHub Copilot (Agent Mode) – requires VS Code 1.99+ and the GitHub Copilot extension.

First, build the project:

npm run build

Then create .vscode/mcp.json in this repository:

{
  "servers": {
    "cloudpulse": {
      "type": "stdio",
      "command": "node",
      "args": ["${workspaceFolder}/dist/index.js"],
      "env": {
        "VERCEL_TOKEN": "${env:VERCEL_TOKEN}",
        "AWS_REGION": "${env:AWS_REGION}",
        "AWS_PROFILE": "${env:AWS_PROFILE}"
      }
    }
  }
}

${env:VAR} reads from your shell environment — no secrets in source control.

To use: open Copilot Chat, switch to Agent mode, click Select Tools and enable the CloudPulse tools, then ask naturally:

Why can't my Vercel project reach AWS RDS instance "my-db"?

Credentials & Security

CloudPulse follows a read-only, no-storage policy:

Credential	How to provide
AWS	`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`, or `AWS_PROFILE`, or EC2 instance role
Vercel	`VERCEL_TOKEN` (personal access token from vercel.com/account/tokens)
Vercel Team	`VERCEL_TEAM_ID` (optional)
GCP	`GOOGLE_APPLICATION_CREDENTIALS`
Cloudflare	`CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID`

No credentials are logged or stored. All values are read from environment variables at call time.

Available Tools

`list_cloud_topology`

Scan all configured platforms and return a unified service map.

Input (all optional):
  platforms       – ["aws", "vercel"]  filter platforms
  aws_region      – "us-east-1"

`get_correlated_logs`

Fetch and merge logs from Vercel + AWS CloudWatch into one timeline.

Input:
  start_time *    – ISO-8601 or epoch ms  e.g. "2024-06-01T10:00:00Z"
  end_time        – defaults to now
  trace_id        – filter by trace/request ID across all sources
  aws_log_group_prefix  – default "/aws/lambda"
  vercel_project  – project name or ID
  aws_region

`diagnose_service_link`

Check why service A can't reach resource B.

Input:
  source_service *  – "vercel" | "lambda" | "ec2" | ...
  target_resource * – "<type>:<id>"  e.g. "aws-rds:my-db", "external-api:https://..."
  port              – auto-detected (5432 for RDS, 443 for APIs, ...)
  vercel_project
  aws_region

Checks performed:

Vercel env vars contain a DATABASE_URL / DB_URL
AWS Security Group allows inbound TCP on the required port
External API HEAD reachability test

`check_resource_limits`

Query quotas and flag resources nearing their limits.

Input (all optional):
  platforms        – filter platforms
  warn_threshold   – usage % to warn at (default 80)
  aws_region

Roadmap

Phase	Status	Scope
1 – MVP	✅ Done	Vercel + AWS (Lambda, RDS, CloudWatch, Security Groups, S3)
2 – Extend	✅ Done	GCP Cloud Run + Cloud SQL + Logging; Cloudflare Workers + Pages; S3 CORS
3 – Intelligence	🔜	Pre-built diagnostic playbooks for CORS, 504 timeout, cold-start loops

Development

git clone https://github.com/Galadriel-Tech-Solutions/cloudpulse-mcp
cd cloudpulse-mcp
npm install
npm run dev        # run from source with tsx
npm run build      # compile to dist/

Project structure

src/
├── index.ts                     # MCP server + tool registration
├── types.ts                     # shared domain types
├── utils.ts                     # concurrency, formatting helpers
├── providers/
│   ├── aws/
│   │   ├── index.ts             # client factory + isAWSConfigured()
│   │   ├── cloudwatch.ts        # CloudWatch Logs
│   │   ├── lambda.ts            # Lambda function listing
│   │   ├── rds.ts               # RDS/Aurora instances & clusters
│   │   ├── ec2.ts               # Security Group inspection
│   │   ├── s3.ts                # S3 buckets + CORS checks
│   │   └── quotas.ts            # Service Quotas API
│   ├── gcp/
│   │   ├── index.ts             # isGCPConfigured() + resolveGCPProject()
│   │   ├── cloud-run.ts         # Cloud Run services
│   │   ├── cloud-sql.ts         # Cloud SQL instances (sqladmin v1beta4)
│   │   └── logging.ts           # Cloud Logging
│   ├── cloudflare/
│   │   └── index.ts             # Pages, Workers, Worker tail logs (WebSocket)
│   └── vercel/
│       └── index.ts             # Vercel REST API v9
└── tools/
    ├── list-cloud-topology.ts
    ├── get-correlated-logs.ts
    ├── diagnose-service-link.ts
    └── check-resource-limits.ts

Adding a new cloud platform

Create src/providers/<platform>/index.ts exporting:
- is<Platform>Configured(): boolean
- Provider-specific data functions
Wire the functions into the relevant tools under src/tools/
Add the platform name to the CloudPlatform union in src/types.ts

CloudPulse MCP Server

CloudPulse MCP Server

Why CloudPulse?

Quick Start

1. Install / run with npx

2. Configure your AI client

Credentials & Security

Available Tools

`list_cloud_topology`

`get_correlated_logs`

`diagnose_service_link`

`check_resource_limits`

Roadmap

Development

Project structure

Adding a new cloud platform

License

Resources

Looking for Admin?

Tools

Latest Blog Posts

MCP directory API