1
Native Go MCP server for Kubernetes and OpenShift: pods, logs, any resource, Helm and more
★ 2.1k · +20 this week · Apache-2.0 · updated 2026-10-02
8.2/10
What it does Kubernetes MCP Server lets a coding agent inspect and manage Kubernetes and OpenShift clusters. It is written in Go and talks to the Kubernetes API server directly, so it does not wrap kubectl or helm and needs neither installed. It reads your kubeconfig or in-cluster credentials, notices when the config changes, and can work across several clusters… Read more →
Pros
- Talks to the Kubernetes API directly, no kubectl or helm needed
- Read-only and no-destructive modes plus denied resources for Secrets
- Optional toolsets for Helm, Tekton, KubeVirt and Kiali
Cons
- Default toolsets include exec and delete, so an unrestricted kubeconfig is risky
- Large tool list can crowd the agent's context unless you trim toolsets
Pricing: Open source · kubernetes openshift helm devops deployment
2
Official MCP server to scaffold, trigger, debug and deploy Trigger.dev tasks from your agent
★ 16k · +50 this week · Apache-2.0 · updated 2026-10-02
8.0/10
What it does Trigger.dev is an open-source platform for durable background jobs, AI agents and workflows written in TypeScript, available as a managed cloud or self-hosted. Its official MCP server connects a coding agent to your Trigger.dev projects, so the agent can search the documentation, set up the SDK in a codebase, trigger and debug task runs, and deploy, all… Read more →
Pros
- Covers docs search, project setup, runs, deployments and analytics queries
- Installer configures many clients automatically
- --readonly and --dev-only flags limit risky tools
Cons
- Requires a Trigger.dev cloud account or self-hosted instance
- Deploy and trigger tools can affect production if not restricted
Pricing: Freemium · background-jobs workflows deploy observability typescript
3
Official suite of AWS MCP servers for docs, CDK, serverless, databases and costs
★ 9.7k · +19 this week · Apache-2.0 · updated 2026-10-02
8.0/10
What it does The awslabs/mcp repository is AWS's open-source collection of MCP servers, and there are dozens of them. Each server covers one AWS area, so you add only what your project needs. Examples include documentation lookup, infrastructure as code, serverless, containers, databases, messaging, monitoring and cost analysis. For vibe coders, the most useful are usually the documentation servers, so… Read more →
Pros
- Official and broad
- Docs and cost servers are useful to everyone on AWS
Cons
- Many servers to choose from
Pricing: Free · aws cloud
🔥 Deal: AWS Activate: up to $200,000 in AWS credits for eligible startups, with extra credits for AI-focused companies
4
Cloudflare's MCP servers for Workers, observability, DNS, docs and more
★ 4.3k · +61 this week · Apache-2.0 · updated 2026-10-01
8.0/10
What it does Cloudflare runs a family of remote MCP servers that connect agents to a Cloudflare account. A useful one for vibe coders is the Workers Bindings server, which lets an agent set up KV, R2, D1 and other resources while it builds a Worker. After deploying, the Builds and Observability servers help the agent find out why a… Read more →
Pros
- Many focused servers
- Hosted with OAuth
Pricing: Freemium · cloud workers
🔥 Deal: Cloudflare for Startups: $10K-$350K in platform credits for early-stage companies (tiered, Series B or earlier)
5
Vercel's official MCP server for projects, deployments, logs and docs
7.8/10
What it does Vercel MCP is Vercel's official Model Context Protocol server, currently in public beta. It is a hosted, remote server at https://mcp.vercel.com that uses OAuth, so there is nothing to install or run locally: your coding agent signs in to your Vercel account and can then work with your projects directly. The typical use is debugging from inside… Read more →
Pros
- Debug deploys from the agent
- Official, OAuth
Cons
- Only Vercel-approved AI clients can connect
- Acts with your full Vercel account permissions; still in beta
Pricing: Freemium · deploy vercel
🔥 Deal: Vercel for Startups: up to $30,000 in credits