devops-infra MCP Server
Define Once. Deploy Anywhere. Govern Automatically. Framework-agnostic platform to build, deploy & govern enterprise AI agents — LangGraph · CrewAI · Claude SDK · OpenAI Agents · Google ADK · AWS · GCP · Azure · K8s · RBAC · A2A · MCP
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
`cloud-run`
✅
`docker-compose`
`kubernetes`
✅
`app-runner`
Status
Cloud vendor
Status
Limited
Status
`cloud` value
Deployer
Description
Build tool
`container-apps`
You write Python
*(n/a — no container)*
Terraform defines it
parallel
fan_out_fan_in agents: triage: ref: agents/triage-agent routes: - condition: billing target: billing - condition: default target: general billing: ref: agents/billing-agent fallback: general general: ref: agents/general-agent shared_state: type: session_context backend: redis deploy: target: gcp ``` Or programmatically with the SDK: ```python from agenthub import Orchestration pipeline = ( Orchestration("support-pipeline", strategy="router", team="eng") .add_agent("triage", ref="agents/triage-agent") .add_agent("billing", ref="agents/billing-agent") .add_agent("general", ref="agents/general-agent") .with_route("triage", condition="billing", target="billing") .with_route("triage", condition="default", target="general") .with_shared_state(state_type="session_context", backend="redis") ) pipeline.deploy() ``` --- ## Install ### PyPI (recommended) ```bash # Full CLI + API server + engine pip install agentbreeder # Lightweight Python SDK only (for programmatic agent definitions) pip install agentbreeder-sdk ``` ### npm (TypeScript / JavaScript) ```bash npm install @agentbreeder/sdk ``` ```typescript import { Agent } from "@agentbreeder/sdk"; const agent = new Agent("customer-support", { version: "1.0.0", team: "eng" }) .withModel({ primary: "claude-sonnet-4", fallback: "gpt-4o" }) .withTool({ ref: "tools/zendesk-mcp" }) .withDeploy({ cloud: "aws", region: "us-east-1" }); await agent.deploy(); ``` ### Homebrew (macOS / Linux) ```bash brew tap agentbreeder/agentbreeder brew install agentbreeder ``` ### Docker **Full platform — no repo clone required:** ```bash curl -O https://raw.githubusercontent.com/agentbreeder/agentbreeder/main/deploy/docker-compose.standalone.yml docker compose -f docker-compose.standalone.yml up -d ``` Dashboard: `http://localhost:3001` · API: `http://localhost:8000` · API Docs: `http://localhost:8000/docs` This pulls pre-built images from Docker Hub (`rajits/agentbreeder-api`, `rajits/agentbreeder-dashboard`), runs database migrations automatically, and wires everything together. **CLI image (for CI/CD pipelines):** ```bash docker pull rajits/agentbreeder-cli docker run rajits/agentbreeder-cli deploy agent.yaml --target gcp ``` --- ## Quick Start ```bash pip install agentbreeder # Scaffold your first agent (interactive wizard — pick framework, cloud, model) agentbreeder init # Validate the config agentbreeder validate agent.yaml # Deploy locally agentbreeder deploy agent.yaml --target local ``` **Or run from source (contributors):** ```bash git clone https://github.com/agentbreeder/agentbreeder.git cd agentbreeder python -m venv venv && source venv/bin/activate pip install -e ".[dev]" cp .env.example .env # Start postgres + redis + API + dashboard (builds from local source) docker compose -f deploy/docker-compose.yml up -d ``` Dashboard: `http://localhost:3001` · API: `http://localhost:8000` · API Docs: `http://localhost:8000/docs` See [docs/quickstart.md](docs/quickstart.md) for the full guide. --- ## CLI 24 commands. Everything you need from scaffold to teardown. ```bash agentbreeder init # Scaffold a new agent project (interactive wizard) agentbreeder validate # Validate agent.yaml without deploying agentbreeder deploy # Deploy an agent (the core command) agentbreeder up / down # Start / stop the full local platform stack agentbreeder status # Show deploy status agentbreeder logs <name> # Tail agent logs agentbreeder list # List agents / tools / models / prompts agentbreeder describe <name> # Show detail for a registry entity agentbreeder search <query> # Search across the entire registry agentbreeder chat <name> # Interactive chat with a deployed agent agentbreeder eval run # Run evaluations (--scorer exact
Who
What it does
Command
Ships
invoke`
Implementing AWS Security Hub to aggregate security findings across AWS accounts, enable compliance standards like CIS AWS Foundations and PCI DSS, configure automated remediation with EventBridge and Lambda, and create custom security insights for organizational risk management.
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
Auditing Microsoft Entra ID (Azure Active Directory) configuration to identify risky authentication policies, overly permissive role assignments, stale accounts, conditional access gaps, and guest user risks using AzureAD PowerShell, Microsoft Graph API, and ScoutSuite.
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.
ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀
Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform
Secure, Fast, and Extensible Sandbox runtime for AI agents.
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
Learn how to use the docker-kubernetes Claude skill. Complete guide with installation instructions and examples.
Learn how to use the cloud-gcp Claude skill. Complete guide with installation instructions and examples.
Learn how to use the cloud-aws Claude skill. Complete guide with installation instructions and examples.