Cloudpulse

Name: Cloudpulse
Author: lhf552004

by lhf552004communityv0.1.2

CloudPulse MCP Server provides read-only cross-cloud visibility and diagnostics for AWS, Vercel, GCP, and Cloudflare. It can map cloud topology, correlate logs across providers, check service connectivity, and flag resources nearing quota limits.

From the registry: Cross-cloud observability for AI agents. Covers AWS, GCP, Vercel, and Cloudflare.

GitHub Repository

Install & configure

Prerequisites

required
Install Node.js 18 or later
CloudPulse requires Node.js 18+ to run via npx.
https://nodejs.org/
optional
Provide cloud credentials
CloudPulse auto-detects credentials already present on your machine. Configure the credentials for the platforms you want to inspect before starting the server.
optional
Create a Vercel personal access token
Required if you want CloudPulse to access Vercel. Generate a token from your Vercel account tokens page.
https://vercel.com/account/tokens

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `cloudpulse` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Node.js 18 or later** — CloudPulse requires Node.js 18+ to run via npx. (https://nodejs.org/)

Optional prerequisites:
- Provide cloud credentials — CloudPulse auto-detects credentials already present on your machine. Configure the credentials for the platforms you want to inspect before starting the server.
- Create a Vercel personal access token — Required if you want CloudPulse to access Vercel. Generate a token from your Vercel account tokens page. (https://vercel.com/account/tokens)

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","cloudpulse-mcp"]
- optional environment variables:
  - `VERCEL_TOKEN`: Vercel personal access token for accessing Vercel resources. (example: `<your-vercel-token>`)
  - `VERCEL_TEAM_ID`: Optional Vercel team ID when accessing team-scoped Vercel resources. (example: `<your-vercel-team-id>`)
  - `AWS_PROFILE`: AWS CLI profile name to use for AWS credentials. (example: `<your-aws-profile>`)
  - `AWS_REGION`: AWS region to use for AWS API calls. (example: `<your-aws-region>`)
  - `AWS_ACCESS_KEY_ID`: AWS access key ID as an alternative to AWS_PROFILE or instance role credentials. (example: `<your-aws-access-key-id>`)
  - `AWS_SECRET_ACCESS_KEY`: AWS secret access key used with AWS_ACCESS_KEY_ID. (example: `<your-aws-secret-access-key>`)
  - `GOOGLE_APPLICATION_CREDENTIALS`: Path to Google Cloud service account credentials file for GCP access. (example: `<path-to-your-gcp-credentials-file>`)
  - `CLOUDFLARE_API_TOKEN`: Cloudflare API token for accessing Cloudflare resources. (example: `<your-cloudflare-api-token>`)
  - `CLOUDFLARE_ACCOUNT_ID`: Cloudflare account ID used with CLOUDFLARE_API_TOKEN. (example: `<your-cloudflare-account-id>`)

Note: Use the npx-based stdio launch path as the canonical configuration. Cloud credentials are platform-specific: only set the environment variables for the providers you want CloudPulse to inspect. AWS credentials may also be supplied implicitly via existing AWS CLI configuration or instance role, so explicit AWS env vars are optional.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: Use the npx-based stdio launch path as the canonical configuration. Cloud credentials are platform-specific: only set the environment variables for the providers you want CloudPulse to inspect. AWS credentials may also be supplied implicitly via existing AWS CLI configuration or instance role, so explicit AWS env vars are optional.

Tools (4)

list_cloud_topology

Scan configured platforms and return a unified map of active services.

get_correlated_logs

Fetch and merge logs from Vercel and AWS CloudWatch into a single timeline.

diagnose_service_link

Check why one service cannot reach another resource and inspect likely network or config causes.

check_resource_limits

Query quotas and warn when resources are nearing their usage limits.

Environment variables

VERCEL_TOKENrequiredVercel personal access token used to access Vercel APIs.

AWS_ACCESS_KEY_IDrequiredAWS access key used for AWS authentication when not using a profile or instance role.

AWS_SECRET_ACCESS_KEYrequiredAWS secret access key used for AWS authentication when not using a profile or instance role.

CLOUDFLARE_API_TOKENrequiredCloudflare API token used to access Cloudflare resources.

CLOUDFLARE_ACCOUNT_IDrequiredCloudflare account identifier required for Cloudflare API access.

GOOGLE_APPLICATION_CREDENTIALSrequiredPath to GCP service account credentials used to access Google Cloud resources.

Packages

cloudpulse-mcp

npmv0.1.2transport: stdio

Details

Language: TypeScript
License: MIT
Released: Apr 19, 2026
Last commit: Apr 19, 2026
Registry name: io.github.lhf552004/cloudpulse

Related Servers

Mcp

Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.

12.0k

Firebase Mcp

Gives AI development tools Firebase-specific capabilities and expertise.

4.4k

Azure MCP Server

All Azure MCP tools to create a seamless connection between AI agents and Azure services.

3.5k